@Article{abelen-etal93, Author="{Abelen, Eric and Redeker, Gisela and Thompson, Sandra A.}", Title="{The rhetorical structure of US-American and Dutch fund-raising letters}", Journal="Text", Volume=13, Number=3, Pages="323-350", Abstract="Presents the results of an anlysis of the RST structures of eight Dutch and eight English fund-raising letters from NPO's. Three classes of relation were observed: interpersonal, ideational, and textual. The American letters showed a higher use of the interpersonal relations, whereas the Dutch letters used more of the ideational and textual relations, leading to the conclusion that the Dutch letters are organised with a greater emphasis on clarity than outright persuasion." Year=1993} @InCollection{afantenos2007, Author="{Afantenos, Stergos D}", Title="{Some reflections on the task of content determination in the context of multi-document summarization of evolving events}", BookTitle="Recent Advances in Natural Language Processing (RANLP 2007)", Editor="Angelova, Galia and Bontcheva, Kalina and Mitkov, Ruslan and Nicolov, Nicolas and Nikolov, Nikolai", Publisher="INCOMA", Address="Borovets, Bulgaria", Pages="12-16", Note="Citation of Taboada and Mann, first paper", Year=2007} @InCollection{afantenos-etal2004, Author="{Afantenos, Stergos D. and Doura, Irene and Kapellou, Eleni and Karkaletsis, Vangelis}", Title="{Exploiting cross-document relations for multi-document evolving summarization}", BookTitle="Methods and Applications of Artificial Intelligence, Proceedings of 3rd Hellenic Conference on AI, SETN 2004", Editor="Vouros, G. A and Panayiotopoulos, T." Series="Lecture Notes in Computer Science", Publisher="Springer", Address="Berlin", Pages="410-419", Note="Cited Reference Count: 7 Cited References: KARKALETSIS V, P 9 PANH C INF PCI 2 MANN WC, 1988, TEXT, V8, P243 MARCU D, 2000, THEORY PRACTICE DISC PAZIENZA MT, 2003, P HUM COMP INT INT H RADEV D, 2000, P 1 ACL SIGDIAL WORK REITER E, 2000, BUILDING NATURAL LAN ZHANG Z, 2002, P AAAI 2002 Article Volume 3025 in Lecture Notes ni Computer Science", Abstract="This paper presents a methodology for summarization from multiple documents which are about a specific topic. It is based on the specification and identification of the cross-document relations that occur among textual elements within those documents. Our methodology involves the specification of the topic-specific entities, the messages conveyed for the specific entities by certain textual elements and the specification of the relations that can hold among these messages. The above resources are necessary for setting up a specific topic for our query-based summarization approach which uses these resources to identify the query-specific messages within the documents and the query-specific relations that connect these messages across documents." Year=2004} @InProceedings{afantenos-herandez, Author="{Afantenos, Stergos D and Hernandez, Nicolas}", Title="{What's in a message?}", Booktitle="Proceedings of the EACL 2009 Workshop on Cognitive Aspects of Computational Language Acquisition", Address="Athens, Greece", Pages="18-25", Year=2009} @Article{afantenos2005, Author="{Afantenos, Stergos D and Karkaletsis, Vangelis and Stamatopoulos, Panagiotis}", Title="{Summarization from medical documents: a survey}", Journal="Artificial Intelligence in Medicine", Volume=33, Number=2, Pages="157-177", Abstract="Objective: The aim of this paper is to survey the recent work in medical documents summarization. Background: During the last decade, documents summarization got increasing attention by the Al research community. More recently it also attracted the interest of the medical research community as well, due to the enormous growth of information that is available to the physicians and researchers in medicine, through the large and growing number of published journals, conference proceedings, medical sites and portals on the World Wide Web, electronic medical records, etc. Methodology: This survey gives first a general background on documents summarization, presenting the factors that summarization depends upon, discussing evaluation issues and describing briefly the various types of summarization techniques. It then examines the characteristics of the medical domain through the different types of medical documents. Finally, it presents and discusses the summarization techniques used so far in the medical domain, referring to the corresponding systems and their characteristics. Discussion and conclusions: The paper discusses thoroughly the promising paths for future research in medical documents summarization. It mainly focuses on the issue of scaling to large collections of documents in various Languages and from different media, on personalization issues, on portability to new sub-domains, and on the integration of summarization technology in practical applications. (c) 2004 Elsevier B.V. All rights reserved." Year=2005} @Article{afantenos-etal2008, Author="{Afantenos, Stergos D. and Karkaletsis, Vangelis and Stamatopoulos, Panagiotis and Halatsis, Constantin}", Title="{Using synchronic and diachronic relations for summarizing multiple documents describing evolving events}", Journal="Journal of Intelligent Information Systems", Volume=30, Number=3, Pages="183-226", Note="Citation of Taboada and Mann ('Looking back..')", Abstract="In this paper we present a fresh look at the problem of summarizing evolving events from multiple sources. After a discussion concerning the nature of evolving events we introduce a distinction between linearly and non-linearly evolving events. We present then a general methodology for the automatic creation of summaries from evolving events. At its heart lie the notions of Synchronic and Diachronic cross-document Relations (SDRs), whose aim is the identification of similarities and differences between sources, from a synchronical and diachronical perspective. SDRs do not connect documents or textual elements found therein, but structures one might call messages. Applying this methodology will yield a set of messages and relations, SDRs, connecting them, that is a graph which we call grid. We will show how such a grid can be considered as the starting point of a Natural Language Generation System. The methodology is evaluated in two case-studies, one for linearly evolving events (descriptions of football matches) and another one for non-linearly evolving events (terrorist incidents involving hostages). In both cases we evaluate the results produced by our computational systems." Year=2008} @InProceedings{ahmed-etal2008, Author="{Ahmed, Nabeel and Khan, Sharifulah and Latif, Khalid and Masood, Asad}", Title="{Extracting semantic annotations and their correlation with document components}", Booktitle="Proceedings of 4th International Conference on Emerging Technologies (ICET)", Address="Rawalpindi, Pakistan", Pages="32-37", Year=2008} @InCollection{allen-etal2005, Author="{Allen, R. B. and Wu, Y. J. and Luo, J.}", Title="{Interactive causal schematics for qualitative scientific explanations}", BookTitle="Digital Libraries: Implementing Strategies and Sharing Experiences, Proceedings", Series="Lecture Notes in Computer Science", Volume=3815, Pages="411-415", Abstract="We present a simple model for describing causal processes. We apply it to generate schematics of complex scientific processes. Our interface allows users to select among causal threads and then to follow the state transitions of those explanations. Moreover, these schematics can provide a framework for interacting with texts." Year=2005} @InProceedings{alonso-fuentes, Author="{Alonso i Alemany, Laura and Fuentes Fort, Maria}", Title="{Integrating cohesion and coherence for automatic summarization}", Booktitle="Proceedings of EACL'03 Student Research Workshop", Address="Budapest, Hungary", Pages="1-8", Year=2003} @InCollection{altenberg2002, Author="{Altenberg, Bengt}", Title="{Concessive connectors in English and Swedish}", BookTitle="Information Structure in a Cross-Linguistic Perspective", Editor="Hasselgård, Hilde and Johansson, Stig and Behrens, Bergljot and Fabricius-Hansen, Cathrine", Publisher="Rodopi", Address="Amsterdam", Pages="21-43", Year=2002} @InProceedings{andre-rist96, Author="{André, Elisabeth and Rist, Thomas}", Title="{Coping with temporal constraints in multimedia presentation planning}", Booktitle="Proceedings of Thirteenth National Conference on Artificial Intelligence", Address="Portland, Oregon", Pages="142-147", Year=1996} @InCollection{andriessen-etal96, Author="{Andriessen, Jerry and de Smedt, Koenraad and Zock, Michael}", Title="{Discourse Planning: Experimental and modeling approaches}", BookTitle="Computational Psycholinguistics: Symbolic and Network Models of Language Processing", Editor="Dijkstra, Ton and de Smedt, Koenraad", Publisher="Taylor and Francis", Address="London", Pages="247-278", Year=1996} @InCollection{androutsopoulos-etal2002, Author="{Androutsopoulos, I. and Spiliotopoulos, D. and Stamatakis, K. and Dimitromanolaki, A. and Karkaletsis, V. and Spyropoulos, C. D.}", Title="{Symbolic authoring for multilingual natural language generation}", BookTitle="Methods and Applications of Artificial Intelligence", Series="Lecture Notes in Artificial Intelligence", Volume=2308, Pages="131-142", Abstract="We describe the symbolic authoring facilities of the M-PIRO project. M-PIRO is developing technology that allows personalized multilingual object descriptions, in both textual and spoken form, to be produced from symbolic information in a database and small fragments of text. The technology is being tested in the context of electronic museums, where a prototype that produces dynamically multilingual exhibit descriptions for presentations over the web has already been developed. This paper focuses on M-PIRO's authoring subsystem, which allows domain experts with no language technology expertise to configure the system for new applications. The authoring facilities allow the experts to define or modify the structure of the underlying database, its contents, and the system's domain-dependent linguistic resources. Previews of the generated texts can also be produced during the authoring process to monitor the content and quality of the resulting descriptions." Year=2002} @Article{antonio2001, Author="{Antonio, Juliano Desiderato}", Title="{A estrutura retorica de textos orais e de textos escritos (Rhetorical structure of oral and written texts)}", Journal="Acta Scientiarum", Volume=23, Number=1, Pages="19-25", Abstract="The goal of this paper is to show that there is an analogy between clause combining in grammar & the rhetorical organization of texts. The analysis of oral & written texts reinforces the hypothesis that the hypotactic & paratactical structures in grammar reflect the grammaticalization of the rhetorical structure of texts. 7 Tables, 4 Figures, 3 Diagrams, 1 Appendix, 15 References. Adapted from the source document", Year=2001} @PhDThesis{antonio-thesis2004, Author="Antonio, Juliano Desiderato", Title="{Estrutura retórica e articulação de orações em narrativas orais e em narrativas escritas do português (Rhetorical structure and clause combining in oral narratives and written narratives in Brazilian Portuguese)}", School="UNESP", Type="Ph.D. dissertation", Year=2004} @Article{arens92, Author="{Arens, Yigal}", Title="{Multimedia Presentation Planning as an Extension of Text Planning}", Journal="Lecture Notes in Artificial Intelligence", Volume=587, Pages="278-280", Year=1992} @Article{arens-hovy95, Author="{Arens, Yigal and Hovy, Eduard}", Title="{The Design of a Model-Based Multimedia Interaction Manager}", Journal="Artificial Intelligence Review", Volume=9, Number=2-3, Pages="167-188", Abstract="We describe here the conceptual design of Cicero, an application-independent human-computer interaction manager that performs run-time media coordination and allocation, so as to adapt dynamically to the presentation context; knows what it is presenting, so as to maintain coherent extended human-machine dialogues; and is plug-in compatible with host information resources such as ''briefing associate'' workstations, expert systems, databases, etc., as well as with multiple media such as natural language, graphics, etc. The system design calls for two linked reactive planners that coordinate the actions of the system's media and information sources. To enable presentational flexibility, the capabilities of each medium and the nature of the contents of each information source are semantically modeled as Virtual Devices - abstract descriptions of device I/O capabilities - and abstract information types respectively in a single uniform knowledge representation framework. These models facilitate extensibility by supporting the specification of new interaction behaviors and the inclusion of new media and information sources." Year=1995} @Article{argamon-etal2008, Author="{Argamon, Shlomo and Dodick, Jeff and Chase, Paul}", Title="{Language use reflects scientific methodology: A corpus-based study of peer-reviewed journal articles}", Journal="Scientometrics", Volume=75, Number=2, Pages="203-238", Abstract="Recently, philosophers of science have argued that the epistemological requirements of different scientific fields lead necessarily to differences in scientific method. In this paper, we examine possible variation in how language is used in peer-reviewed journal articles from various fields to see if features of such variation may help to elucidate and support claims of methodological variation among the sciences. We hypothesize that significant methodological differences will be reflected in related differences in scientists' language style. This paper reports a corpus-based study of peer-reviewed articles from twelve separate journals in six fields of experimental and historical sciences. Machine learning methods were applied to compare the discourse styles of articles in different fields, based on easily-extracted linguistic features of the text. Features included function word frequencies, as used often in computational stylistics, as well as lexical features based on systemic functional linguistics, which affords rich resources for comparative textual analysis. We found that indeed the style of writing in the historical sciences is readily distinguishable from that of the experimental sciences. Furthermore, the most significant linguistic features of these distinctive styles are directly related to the methodological differences posited by philosophers of science between historical and experimental sciences, lending empirical weight to their contentions." Year=2008} @Book{asher93, Author="{Asher, Nicholas}", Title="Reference to Abstract Objects in Discourse", Publisher="Kluwer", Address="Dordrecht", Year=1993} @InProceedings{asher-etal2008, Author="{Asher, Nicholas and Benamara, Farah and Mathieu, Yvette Yannick}", Title="{Distilling opinion in discourse: A preliminary study}", Booktitle="Proceedings of COLING", Address="Manchester, UK", Pages="7-10", Year=2008} @InProceedings{asher-etal-ecai2008, Author="{Asher, Nicholas and Benamara, Farah and Mathieu, Yvette Yannick}", Title="{Categorizing opinion in discourse}", Booktitle="Proceedings of the 18th European Conference on Artificial Intelligence (ECAI 2008)", Address="Patras, Greece", Pages="835-836", Year=2008} @Article{asheretal2009, Author="{Asher, Nicholas and Benamara, Farah and Mathieu, Yvette Yannick}", Title="{Appraisal of opinion expressions in discourse}", Journal="Linguisticae Investigationes", Volume=32, Number=2, Pages="279-292", Year=2009} @InProceedings{asher-lascarides94, Author="{Asher, Nicholas and Lascarides, Alex}", Title="{Intentions and information in discourse}", Booktitle="Proceedings of 32nd Meeting of the Association for Computational Linguistics (ACL'94)", Address="Las Cruces, New Mexico", Pages="34-41", Year=1994} @Book{asher-lascarides-book2003, Author="{Asher, Nicholas and Lascarides, Alex}", Title="Logics of Conversation", Publisher="Cambridge University Press", Address="Cambridge", Year=2003} @Article{asher-etal2007, Author="{Asher, Nicholas and Prévot, Laurent and Vieu, Laure}", Title="{Setting the background in discourse}", Journal="Discours", Volume=1, Pages="[Online], Put online on 03 April 2008. URL : http://discours.revues.org//index301.html. Consulted on 08 May 2008." Note="Citation of Taboada and Mann, part 1", Year=2007} @Article{azar99, Author="{Azar, Moshe}", Title="{Argumentative text as rhetorical structure: An application of Rhetorical Structure Theory}", Journal="Argumentation", Volume=13, Number=1, Pages="97-144", Abstract="Investigates five RST relations (Evidence, Motivation, Justify, Antithesis, Concession) and their logical/pragmatic equivalents in the realm of argumentation (supportive, incentive, justifier, persuader (last two)) . Paper includes analyses of three sample texts. Another: Rhetorical structure theory, as a tool for analyzing written texts, is particularly appropriate for analyzing argumentative texts. The distinction that rhetorical structure theory makes between the part of a text that realizes the primary goal of the writer, termed nucleus, & the part that provides supplementary material, termed satellite, is crucial for the analysis of argumentative texts. The paper commences by determining the concept of argument relation (argument + conclusion) & by briefly presenting rhetorical structure theory. It continues by identifying five of rhetorical structure theory's rhetorical relations of the satellite/nucleus schema (evidence, motivation, justify, antithesis, concession) as five argument relations, each being, logically or pragmatically, a special kind of argument: evidence is a supportive argument, motivation is an incentive argument, justify is a justifier argument, & antithesis & concession are persuader arguments. To illustrate, an analysis of three short texts concludes the paper. 4 Figures, 36 References. Adapted from the source document", Year=1999} @Article{babaii2007, Author="{Babaii, Esmat}", Title="{Review of: Taboada, M. (2004) Building Coherence and Cohesion}", Journal="Discourse and Society", Volume=18, Number=2, Pages="223-237", Note="Review of my book", Year=2007} @Article{baldrige-etal2007, Author="{Baldridge, Jason and Asher, Nicholas and Hunter, Julie}", Title="{Annotation for and robust parsing of discourse structure on unrestricted texts}", Journal="Zeitschrift für Sprachwissenschaft", Number=26, Pages="213-239", Year=2007} @Article{longacre71a, Author="{Ballard, D. Lee and Conrad, Robert J. and Longacre, Robert E.}", Title="{Interclausal relations}", Journal="Foundations of Language", Volume=7, Number=1, Pages="70-118", Year=1971} @Book{longacre71b, Author="{Ballard, D. Lee and Conrad, Robert J. and Longacre, Robert E.}", Title="More on the Deep and Surface Grammar of Interclausal Relations", Publisher="Summer Institute of Linguistics", Address="Santa Ana, CA", Abstract="Language Data, Asian-Pacific series", Year=1971} @InCollection{barenfanger-etal2006, Author="{Bärenfänger, Maja and Hilbert, Mirco and Lobin, Henning and Lüngen, Harald and Puskás, Csilla}", Title="{Cues and constraints for the relational discourse analysis of complex text types: The role of logical and generic document structure}", BookTitle="Proceedings of the Workshop on Constraints in Discourse", Editor="Sidner, Candace L and Harpur, John and Benz, Anton and Kühnlein, Peter", Address="Maynooth, Ireland", Pages="27-34", Note="Citation of: web site, Taboada and Lavid 2003", Year=2006} @InProceedings{barenfanger-etal-workshop2005, Author="{Bärenfänger, Maja and Lobin, Henning and Lüngen, Harald and Hilbert, Mirco}", Title="{Using OWL ontologies in discourse parsing}", Booktitle="Proceedings of the Workshop of Ontologies in Text Technology", Address="Osnabrück, Germany", Year=2006} @InProceedings{barzilay-lapata2005, Author="{Barzilay, Regina and Lapata, Mirella}", Title="{Modeling local coherence: An entity-based approach}", Booktitle="Proceedings of the 43rd Meeting of the Association for Computational Linguistics", Address="Ann Arbor, MI", Pages="141-148", Year=2005} @Article{barzilay-lapata2008, Author="{Barzilay, Regina and Lapata, Mirella}", Title="{Modeling local coherence: An entity-based approach}", Journal="Computational Linguistics", Volume=34, Number=1-34, Abstract="This article proposes a novel framework for representing and measuring local coherence. Central to this approach is the entity-grid representation of discourse, which captures patterns of entity distribution in a text. The algorithm introduced in the article automatically abstracts a text into a set of entity transition sequences and records distributional, syntactic, and referential information about discourse entities. We re-conceptualize coherence assessment as a learning task and show that our entity-based representation is well-suited for ranking-based generation and text classification tasks. Using the proposed representation, we achieve good performance on text ordering, summary coherence evaluation, and readability assessment", Year=2008} @InProceedings{bateman90, Author="{Bateman, John}", Title="{Finding translation equivalents: An application of grammatical metaphor}", Booktitle="Proceedings of 13th International Conference on Computational Linguistics (COLING'90)", Address="Helsinki, Finland", Pages="13-18", Year=1990} @InCollection{bateman-delin-rst-enc, Author="{Bateman, John and Delin, Judy}", Title="{Rhetorical structure theory}", BookTitle="Encyclopedia of Language and Linguistics", Publisher="Elsevier", Address="Oxford", Edition="2nd", Pages="589-596", Year=2005} @InProceedings{bateman-etal2000, Author="{Bateman, John and Delin, Judy and Allen, Patrick}", Title="{Constraints on layout in multimodal document generation}", Booktitle="Proceedings of First International Natural Language Generation Conference, Workshop on Coherence in Generated Multimedia", Address="Mitzpe Ramon, Israel", Year=2000} @Article{bateman-etal2001, Author="{Bateman, John and Kamps, Thomas and Kleinz, Jörg and Reichenberger, Klaus}", Title="{Towards constructive text, diagram, and layout generation for information presentation}", Journal="Computational Linguistics", Volume=27, Number=3, Pages="409-449", Abstract="First discusses a general method of organising the informational strucutre to be presented, which then informs a text/graphic/layout generation system. Example analyses and pages are given to illustrate the links between layout and RST, as well as sample output of the program." Year=2001} @Article{bateman-rondhuis97, Author="{Bateman, John and Rondhuis, Klaas Jan}", Title="{Coherence relations: Towards a general specification}", Journal="Discourse Processes", Volume=24, Pages="3-49", Abstract="Assesses the "State of the Union" in coherence relation analysis, from functional linguistics to formal semantic discourse theory. Organizes the information found into three categories: linguistic "stratification", "metafunction", and "paradigmatic/syntagmatic axiality". Also points out problem areas for future computational specification." Year=1997} @Article{baumgarten2007, Author="{Baumgarten, N.}", Title="{Converging conventions? Macrosyntactic conjunction with English and and German und}", Journal="Text & Talk", Volume=27, Number=2, Pages="139-170", Note="Cited References: AIJMER K, 2006, PRAGMATIC MARKERS CO AMMON U, 1994, ENGLISH ONLY EUROPA BAUMGARTEN N, 2005, SECRET AGENT FILM DU BIBER D, 1989, LINGUISTICS, V27, P3 BIBER D, 1999, GRAMMAR SPOKEN WRITT BLAKEMORE D, 1999, UCL WORKING PAPERS L, V11, P1 BLAKEMORE D, 2005, LINGUA, V115, P569, DOI 10.1016/j.lingua.2003.09.016 BOTTGER C, 2002, ZEITENWENDE GERMANIS, P253 BYRNES H, 1986, TEXT, V6, P89 CARSTENSEN B, 1975, AMERIKANISMEN DTSCH CHWITALLA J, 1997, GESPROCHENES DTSCH E CLYNE M, 1987, J PRAGMATICS, V11, P101 CLYNE M, 1991, SUBJECT ORIENTED TEX, P49 CLYNE M, 1994, INTERCULTURAL COMMUN DOHERTY M, 1995, STILFRAGEN, P181 DOHERTY M, 1996, LINGUISTICS, V34, P591 DOHERTY M, 2002, LANGUAGE PROCESSING DOHERTY M, 2003, ACROSS LANGUAGES CUL, V4, P19 DORGELOH H, 2004, J PRAGMATICS, V36, P1761, DOI 10.1016/j.pragma.2004.04.004 DRESCHER M, 2003, GRUPPENSTILE SPRACHL, P53 ECKERT P, 2005, ANN M LING SOC AM OA EHLICH K, 1992, COOPERATING WRITTEN, P201 EHLICH K, 2005, ENGLISCH ODER DTSCH, P41 FABRICIUSHANSEN C, 1909, SPRACHSPEZIFISCHE AS, P175 FABRICIUSHANSEN C, 2000, WISSENSCHAFTSSPRACHE FABRICIUSHANSEN C, 2005, LINGUISTICS, V43, P17 FRASER B, 1999, J PRAGMATICS, V31, P931 GARDT A, 2004, GLOBALIZATION FUTURE GIVON T, 1990, SYNTAX FUNCTIONAL TY GRAEFEN G, 1994, TEXTE DISKURSE METHO, P136 HALLIDAY M, 1976, COHESION ENGLISH HALLIDAY M, 1994, INTRO FUNCTIONAL GRA HOSUE J, 1989, CROSS CULTURAL PRAGM, P96 HOUSE J, 1996, CONTRASTIVE SOCIOLIN, P345 HOUSE J, 2003, J SOCIOLING, V7, P556 HOUSE J, 2004, MEDIAZIONE LINGUISTI, P21 HYLAND K, 1998, J PRAGMATICS, V30, P437 HYLAND K, 2004, APPL LINGUIST, V25, P156 KOLLER W, 2000, SPRACHGESCHICHTE HDB, P112 KOTTHOFF H, 1989, PRO KONTRA FREMDSPRA LANG E, 1977, SEMANTIK KOORDINATIV MANN WC, 1987, RHETORICAL STRUCTURE MANN WC, 1988, TEXT, V8, P243 PETERS P, 2004, CAMBRIDGE GUIDE ENGL QUIRK R, 1985, COMPREHENSIVE GRAMMA REDEKER G, 1990, J PRAGMATICS, V14, P367 REHBEIN J, 1989, BIOGRAPHIEN KOMPLEXE, P163 SCHIFFIN D, 1987, DISCOURSE MARKERS SCHIFFRIN D, 1986, J PRAGMATICS, V10, P41 STRECKER B, 1997, GRAMMATIK DTSCH SPRA THOMPSON G, 1995, TEXT, V15, P103 THOMPSON G, 2001, APPL LINGUIST, V22, P58 WERINRICH H, 2003, TEXTGRAMMATIK DTSCH Article", Abstract="A growing number of investigations into,the historical development and status of academic prose have found that many national languages lose both prestige and distribution as a medium of expression in the sciences, while English progressively develops into the lingua franca of science. The investigation presented in this paper starts from the assumption that the status of English as a global lingua franca not only replaces the use of other languages but that the prestige associated with English styles of scientific writing can also influence text production in other languages in the sense that indigenous language-and culture-specific communicative conventions are superseded by the conventions operative in comparable English texts. Taking the example of macrosyntactic conjunction with and and und in English and German popular scientific texts, this article addresses the question of whether German communicative conventions are adapted to English communicative styles such that language-specific strategies of information organization in German change in the direction of English." Year=2007} @Book{beekman-callow, Author="{Beekman, John and Callow, John}", Title="Translating the Word of God", Publisher="Zondervan Publishing House", Address="Grand Rapids, MI", Year=1974} @InProceedings{bell-website, Author="{Bell, Mark A.}", Title="Online notes on the structure of argument essays", Volume=2004, Number=June 25, Year=2001} @Article{benwell99, Author="{Benwell, Bethan}", Title="{The organisation of knowledge in British university tutorial discourse: Issues, pedagogic discourse strategies and disciplinary identity}", Journal="Pragmatics", Volume=9, Number=4, Pages="535-565", Abstract="Spoken tutorial discourse is argued to be describable in terms of topic or information hierarchies that can be linked via a finite series of rhetorical relations or "pedagogic discourse strategies." The dialogue from British university tutorials in physics & English literature was used to (1) explore a model of knowledge structuring in spoken tutorial interaction, (2) provide a formal description of how knowledge is structured in two contrastive subject (science & art) tutorials, & (3) describe how this structuring relates in predictable ways to subject methodology. Here the American Rhetorical Structure Theory of W. C. Mann & S. Thompson (1985, 1986, & 1992), generally applied to coherent texts, was used as a starting point for development of a spoken discourse framework with provisions for repetition & for the consequences of clarification or repair. Data were gathered from a physics tutorial & an English literature tutorial, each lasting one hour, involving 8 & 6 students, respectively. Whereas the physics tutorial was characterized by a global pattern of subordination or recursive embedding, the English literature tutorial reflected a coordination of issues. Each tutorial was therefore seen to reflect the core structure of its discipline, the physics tutorial an atomistic process involving accretion of knowledge by pieces, & the English tutorial revealing an organic or holistic structure. 3 Figures, 43 References. L. R. Hunter", Year=1999} @Article{berber-sardinha2006, Author="{Berber Sardinha, Tony}", Title="{Review of: Taboada, M. (2004) Building Coherence and Cohesion}", Journal="Computational Linguistics", Volume=32, Number=2, Pages="283-286", Year=2006} @Book{bernardez95, Author="{Bernárdez, Enrique}", Title="Teoría y epistemología del texto", Publisher="Cátedra", Address="Madrid", Year=1995} @InProceedings{berzlanovich-etal2008, Author="{Berzlánovich, Ildikó and Egg, Markus and Redeker, Gisela}", Title="{Coherence structure and lexical cohesion in expository and persuasive texts}", Booktitle="Proceedings of the Workshop on Constraints in Discourse", Address="Potsdam, Germany", Pages="19-26", Year=2008} @Article{beveridge-fox2006, Author="{Beveridge, Michael and Fox, John}", Title="{Automatic generation of spoken dialogue from medical plans and ontologies}", Journal="Journal of Biomedical Informatics", Volume=39, Number=5, Pages="482-499", Abstract="This paper presents some research undertaken as part of the EU-funded HOMEY project, into the application of intelligent dialogue systems to healthcare systems. The work presented here concentrates on the ways in which knowledge of underlying task structure (e.g., a medical guideline) can be combined with ontological knowledge (e.g., medical semantic dictionaries) to provide a basis for the automatic generation of flexible and re-configurable dialogue. This approach is next evaluated via a specific application that provides decision support to general practitioners to help determine whether or not a patient should be referred to a cancer specialist. The competence of the resulting dialogue application, its speech recognition performance, and dialogue performance are all evaluated to determine the applicability of this approach. (c) 2006 Elsevier Inc. All rights reserved." Year=2006} @InCollection{beveridge-etal2003, Author="{Beveridge, Michael and Fox, John and Milward, David}", Title="{Speech interfaces for point-of-care guideline systems}", BookTitle="Artificial Intelligence in Medicine, Proceedings", Series="Lecture Notes in Artificial Intelligence", Volume=2780, Pages="76-80", Abstract="A major limiting factor in the acceptability of interactive guideline and decision support systems is the case of use of the system in the clinic. A way to reduce demands upon users and increase flexibility of the interface is to use natural language dialogues and speech based interfaces. This paper describes a voice-based data capture and decision support system in which knowledge of underlying task structure (a medical guideline) and domain knowledge (disease ontologies and semantic dictionaries) are integrated with dialogue models based on conversational game theory resulting in a flexible and configurable interface." Year=2003} @InCollection{beveridge-milward2003, Author="{Beveridge, Martin and Milward, David}", Title="{Combining task descriptions and ontological knowledge for adaptive dialogue}", BookTitle="Text, Speech and Dialogue, Proceedings", Series="Lecture Notes in Artificial Intelligence", Volume=2807, Pages="341-348", Abstract="This paper investigates the use. of abstract task specifications for dialogue management in the medical domain. In most current dialogue systems, possible interactions with the system are hand-coded in the design. This is an expensive process, especially for complex dialogues. This paper motivates the use of a task description language for building flexible and adaptive dialogue systems in ontologically rich domains such as medicine. It describes the components of a task specification, and proposes an architecture for dialogue systems which al-lows integration of domain reasoning and dialogue. A high-level dialogue specification is used to support multimodal input and output, including generation of HTML pages, and generation of fragments of VoiceXML for spoken in-teraction." Year=2003} @Article{bille2005, Author="{Bille, Philip}", Title="{A survey on tree edit distance and related problems}", Journal="Theoretical Computer Science", Volume=337, Number=1-3, Pages="217-239", Year=2005} @Article{binnick2009, Author="{Binnick, Robert}", Title="{Altaic hypotaxis and the expression of rhetorical relations}", Journal="Toronto Working Papers in Linguistics", Volume=34, Note="Citation of: JofPrags 2006", Year=2009} @Article{blakemore2007, Author="{Blakemore, Diane}", Title="{Or'-parentheticals, 'that is'-parentheticals and the pragmatics of reformulation}", Journal="Journal of Linguistics", Volume=43, Number=2, Pages="311-339", Abstract="The classification of that is, or (in other words), and or rather as reformulation markers would seem to suggest that the utterances they introduce achieve relevance in the same way. However, the examination of a range of discrepancies between reformulations introduced by or, on the one hand, and reformulations introduced by that is, on the other, suggests that any account of the pragmatics of reformulation must be a non-unitary one. In this paper, I build on Burton-Roberts' (1993) suggestion that the reformulations introduced by or are meta-linguistic in character, and show how these can be distinguished from the reformulations introduced by that is, which must be analysed at the level of conceptual representation. I also show how this distinction corresponds to a distinction between the different ways in which a parenthetical construction may be pragmatically integrated with its host. As Potts (2005) would predict, parenthetical that is-reformulations are not themselves part of the truth-conditional content of their hosts. However, in contrast with or-reformulations, they communicate information about the propositional content of their hosts, and in this way can contribute to the identification of their truth-conditional content at the level of pragmatic interpretation." Year=2007} @InCollection{bluhdorn2007, Author="{Blühdorn, Hardarik}", Title="{Subordination and coordination in syntax, semantics and discourse: Evidence from the study of connectives}", BookTitle="'Subordination' versus 'Coordination' in Sentence and Text." Editor="Fabricius-Hansen, Cathrine and Ramm, Wiebke", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="to appear", Note="Citation of Taboada and Mann, 'Looking back...'", Year=2007} @Article{bocaniala2000, Author="{Bocaniala, Cosmin Danut}", Title="{The textual idea and its relationship to discourse structure}", Journal="The Annals of University “Dunarea de Jos” of Galati, Fascicle III", Volume=2000, Number=1, Pages="75-79", Abstract="Introduces an RST-inspired means of representing discourse strucutre. Essentially there are two relations, continue and detail, which are represented graphically in a hierarchical connected graph. Summarization is then achieved by slicing layers from the top down." Year=2000} @TechReport{borst2006, Author="{Borst, Timo}", Title="{Ontologien zur semantischen Auszeichnung digitaler Lernmaterialien}", Institution="FernUniversität in Hagen, Germany", Type="Technical Report", Year=2006} @Article{boscolo95, Author="{Boscolo, P.}", Title="{The Cognitive Approach to Writing and Writing Instruction - a Contribution to a Critical-Appraisal}", Journal="Cahiers De Psychologie Cognitive-Current Psychology of Cognition", Volume=14, Number=4, Pages="343-366", Note="Cited Reference Count: 91 Cited References: ACKERMAN JM, 1991, RES TEACH ENGL, V25, P133 ADAM JM, 1992, TEXTES TYPES PROTOTY ANDRIESSEN JEB, 1991, MINIMAL STRATEGIES C APPLEBEE AN, 1986, TEACHING WRITING, P95 BANGERTDROWNS RL, 1993, REV EDUC RES, V63, P69 BEAUGRANDE RD, 1984, TEXT PRODUCTION BENTON SL, 1993, J EDUC PSYCHOL, V85, P267 BEREITER C, 1982, ADV INSTRUCTIONAL PS, V2 BEREITER C, 1980, COGNITIVE PROCESS, P73 BEREITER C, 1987, PSYCHOL WRITTEN COMP BERNINGER VW, 1991, READ WRIT, V3, P115 BERNINGER VW, 1992, READING WRITING, V4, P25280 BOSCOLO P, IN PRESS CHILDRENS E BOSCOLO P, 1990, 1 LANGUAGE, V10, P217 BRACEWELL RJ, 1983, RES WRITING PRINCIPL, P436 BRACEWELL RJ, 1980, VISIBLE LANG, V14, P400 BRITTON JN, 1975, DEV WRITING ABILITIE BRONCKART JP, 1985, FONCTIONNEMENT DISCO BRYSON M, 1991, COMPLEX PROBLEM SOLV, P61 CARAMAZZA A, 1990, COGNITION, V37, P243 CARTER M, 1990, COLL COMPOS COMMUN, V41, P265 CHANQUOY L, 1990, CAH PSYCHOL COGN, V10, P513 CHAROLLES M, 1983, TEXT, V3, P71 CHESNET D, 1994, ANN PSYCHOL, V94, P283 COCHRANSMITH M, 1991, REV EDUC RES, V61, P107 COLLINS A, 1980, COGNITIVE PROCESS, P51 COX BE, 1991, RES TEACH ENGL, V25, P179 DAIUTE C, 1986, RES TEACH ENGL, V20, P141 DEBERNARDI B, 1991, EUROPEAN J PSYCHOL E, V6, P143 DEBERNARDI B, IN PRESS ARGUMENTATI DYSON AH, 1991, HDB RES TEACHING ENG, P754 DYSON AH, 1991, RES TEACH ENGL, V25, P97 EIGLER G, 1991, EUROPEAN J PSYCHOL E, V6, P225 ELLIS AW, 1988, HUMAN COGNITIVE NEUR ELLIS AW, 1987, PERSPECTIVES COGNITI, P189 ELLIS AW, 1984, READING WRITING DYSL EMIG J, 1971, COMPOSING PROCESS 12 ENGLERT CS, 1988, EXCEPT CHILDREN, V54, P513 ENGLERT CS, 1988, LEARNING DISABILITY, V11, P18 ESPERET E, 1989, LEARNING INSTRUCTION FARR M, 1993, WRIT COMMUN, V10, P4 FAYOL M, 1991, EUROPEAN J PSYCHOL E, V6, P101 FITZGERALD J, 1987, COGNITION INSTRUCT, V4, P3 FITZGERALD J, 1992, PROMOTING ACAD COMPE, P337 FITZGERALD J, 1986, RES TEACH ENGL, V20, P263 FITZGERALD J, 1987, REV EDUC RES, V57, P481 FLOWER L, 1983, RES WRITTEN LANGUAGE, P206 GALBRAITH D, 1992, INSTR SCI, V21, P45 GLASER R, 1991, TESTING COGNITION, P17 GRAESSER AC, 1985, UNDERSTANDING EXPOSI GUFONI W, 1994, THESIS U BOURGOGNE HARRIS KR, 1992, HELPING YOUNG WRITER HASAN R, 1984, UNDERSTANDING READIN, P181 HAWISHER GE, 1989, CRITICAL PERSPECTIVE HAYES JR, 1987, ADV APPLIED PSYCHOLI, V2, P176 HAYES JR, 1980, COGNITIVE PROCESS, P4 HIDI S, 1983, CURRICULUM INQ, V13, P377 HIGGINS L, 1992, WRIT COMMUN, V9, P48 HOBBS JR, 1982, STRATEGIES NATURAL L, P223 JORAM E, 1992, RES TEACH ENGL, V26, P167 KELLOGG RT, 1994, PSYCHOL WRITING KIEWRA KA, 1989, EDUC PSYCHOL REV, V1, P147 KINTSCH W, 1982, READING EXPOSITORY M, P87 KOZMA RB, 1991, COGNITION INSTRUCT, V8, P1 MANN WC, 1988, TEXT, V8, P243 MATSUHASHI A, 1982, WHAT WRITERS KNOW LA, P269 MATSUHASHI A, 1987, WRITING REAL TIME MCCUTCHEN D, 1986, J MEM LANG, V25, P431 MCCUTCHEN D, 1982, TEXT, V2, P113 MCLANE JB, 1990, VYGOTSKY ED INSTRUCT, P304 MEYER BJF, 1975, ORG PROSE ITS EFFECT MICELI G, 1994, NEUROPSYCHOLOGIA, V32, P317 NEWKIRK T, 1987, RES TEACH ENGL, V21, P121 NYSTRAND M, 1989, WRIT COMMUN, V6, P66 PONTECORVO C, 1991, EUROPEAN J PSYCHOL E, V6, P199 ROUSSEY JY, 1990, LANGUAGE ED, V4, P51 SANDERS TJM, 1992, DISCOURSE PROCESS, V15, P1 SCARDAMALIA M, 1991, GEN THEORY EXPERTISE, P172 SCARDAMALIA M, 1986, HDB RES TEACHING, P778 SCHUMACHER GM, 1992, READING EMPIRICAL RE, P249 SCHUMACHER GM, 1991, RES TEACH ENGL, V25, P67 SCINTO LFM, 1986, WRITTEN LANGUAGE PSY SPIEGEL DL, 1990, RES TEACH ENGL, V24, P48 STEIN N, 1986, REV RES EDUC, V13, P225 STEINBERG ER, 1986, COLL ENGL, V48, P697 STOTSKY S, 1990, COLL COMPOS COMMUN, V41, P37 SWARTS H, 1984, NEW DIRECTIONS COMPO, P53 TANNEN D, 1984, COHERENCE SPOKEN WRI VANDIJK TA, 1985, HDB DISCOURSE ANAL, V2, P103 WEAVER CA, 1991, HDB READING RES, V2, P230 ZAMMUNER VL, 1990, LEARNING INSTRUCTION, P309 Article", Abstract="Research on writing has been greatly stimulated by cognitive psychology, in which writing has been conceptualized as a problem solving activity. The objective of this paper is to critically analyze some aspects of the cognitive approach to writing and writing instruction: (1) the effects of problem solving analogy in writing research; (2) the lack of a comprehensive theory of writing development; and (3) good vs. competent writing. In the cognitive approach the main objective of writing instruction is to make the pupil into a strategic writer, whereas writing itself is viewed as subordinate to learning and thinking. The concept of writing expertise is analyzed and some suggestions for research on writing instruction are discussed." Year=1995} @InProceedings{bosma2005, Author="{Bosma, Wauter E.}", Title="{Extending answers using discourse structure}", Booktitle="Proceedings of RANLP Workshop on Crossing Barriers in Text Summarization Research", Pages="2-9", Year=2005} @InProceedings{bosma-clin2005, Author="{Bosma, Wauter E.}", Title="{Query-based summarization using Rhetorical Structure Theory}", Booktitle="Proceedings of 15th Meeting of CLIN", Pages="29-44", Year=2005} @PhDThesis{bosma2008, Author="Bosma, Wauter E." Title="{Discourse oriented summarization}", School="University of Twente", Type="Ph.D. dissertation", Year=2008} @InProceedings{bouayad-agha, Author="{Bouayad-Agha, Nadjet}", Title="{Using an abstract rhetorical representation to generate a variety of pragmatically congruent texts}", Booktitle="Proceedings of the 38th Meeting of the Association for Computational Linguistics (ACL'00), Student Workshop", Address="Hong Kong", Pages="16-22", Year=2000} @InProceedings{bouayad-agha-etal2000, Author="{Bouayad-Agha, Nadjet and Power, Richard and Scott, Donia}", Title="{Can text structure be incompatible with rhetorical structure?}", Booktitle="Proceedings of International Conference in Natural Language Generation (INLG-2000)", Address="Mitzpe Ramon, Israel", Pages="194-200", Year=2000} @InCollection{bouwer98, Author="{Bouwer, A.}", Title="{An ITS for Dutch punctuation}", BookTitle="Intelligent Tutoring Systems", Series="Lecture Notes in Computer Science", Volume=1452, Pages="224-233", Note="Cited Reference Count: 11 Cited References: BOUWER A, 1996, THESIS VRIJE U AMSTE BRISCOE T, 1996, ACL SIGP INT M PUNCT, P1 MANN WC, 1988, TEXT, V8, P243 MARCU D, 1997, THESIS U TORONTO NUNBERG G, 1990, CSLI LECT NOTES, V18 ONRUST M, 1993, DOCENTENHANDLEIDING ONRUST M, 1993, FORMULEREN SHUAN PL, 1996, ACL SIGP INT M PUNCT, P57 SIMARD M, 1996, ACL SIGPARSE INT M P, P67 VANDERHORST PJ, 1990, LEESTEKENWIJZER VERVOORN AJ, 1991, PRISMA LEESTEKENS HO Article", Abstract="This paper describes a prototype Intelligent Teaching System aimed at improving Dutch university students' use of punctuation in writing and editing texts. Not only grammatical aspects of punctuation are considered, but also the effect of using different punctuation marks with respect to the rhetorical structure of the text. The system offers a student texts in which he should check the punctuation, and if necessary, make corrections. The system then analyses the student's answer and the differences with respect to possible correct solutions, and gives specific feedback based on these analyses. Formative evaluation of the prototype suggests that it has some advantages over using textbooks, because it allows students to understand the way punctuation actually works, rather than merely teaching prescriptive rules." Year=1998} @Article{britton-etal82, Author="{Britton, Bruce K. and Glynn, Shawn M. and Meyer, Bonnie J. F. and Penland, M. J.}", Title="{Effects of text structure on use of cognitive capacity during reading}", Journal="Journal of Educational Psychology", Volume=74, Number=1, Pages="51-61", Abstract="In three experiments, the demand that text processing imposes on learners' cognitive capacity was measured with a secondary-task technique. In all experiments, the meaning of the textual materials was held constant while several structural (surface) variables were manipulated. Experiment 1 showed that text versions with simplified vocabulary and syntax (but equivalent content) required less cognitive capacity to process than standard versions. Experiment 2 revealed that the reduction in use of cognitive capacity observed in Experiment 1 was due primarily to syntactic factors. Finally, Experiment 3 demonstrated that texts containing signals about idea importance and idea relations required less cognitive capacity to process than texts with approximately the same propositional content, but no such signals. In each experiment, measures of total inspection time and content recall were also secured. In general, the findings of all three experiments indicated that aspects of the surface structure of text made demands on the reader's cognitive processing capacity." Year=1982} @Article{bruhn-de-garavito2004, Author="{Bruhn de Garavito, Joyce}", Title="{Review of: Taboada, M. (2004) Building Coherence and Cohesion}", Journal="University of Toronto Quarterly", Volume=75, Number=1, Pages="184-186", Year=2006} @Article{burstein-marcu-knight2003, Author="{Burstein, Jill and Marcu, Daniel and Knight, Kevin}", Title="{Finding the WRITE stuff: Automatic identification of discourse structure in student essays}", Journal="Ieee Intelligent Systems", Volume=18, Number=1, Pages="32-39", Year=2003} @InProceedings{burstein-etal-patent2001, Author="{Burstein, Jill C. and Braden-Harder, Lisa and Chodorow, Martin and Kaplan, Bruce A. and Kukich, Karen and Lu, Chi and Rock, Donald A. and Wolff, Susanne}", Title="System and method for computer-based automatic essay scoring", Publisher="Educational Testing Services", Abstract="A method of grading an essay using an automated essay scoring system is provided. The method comprises the automated steps of (a) parsing the essay to produce parsed text, wherein the parsed text is a syntactic representation of the essay, (b) using the parsed text to create a vector of syntactic features derived from the essay, (c) using the parsed text to create a vector of rhetorical features derived from the essay, (d) creating a first score feature derived from the essay, (e) creating a second score feature derived from the essay, and (f) processing the vector of syntactic features, the vector of rhetorical features, the first score feature, and the second score feature to generate a score for the essay. The essay scoring system comprises a Syntactic Feature Analysis program which creates a vector of syntactic features of the electronic essay text, a Rhetorical Feature Analysis program which creates a vector of rhetorical features of the electronic essay text, an EssayContent program which creates a first Essay Score Feature, an ArgContent program which creates a second Essay Score Feature, and a scoring engine which generates a final score for the essay from the vector of syntactic features, the vector of rhetorical features, the first score feature, and the second score feature." Year=2001} @InProceedings{burstein-etal-patent2002, Author="{Burstein, Jill C. and Braden-Harder, Lisa and Chodorow, Martin S. and Kaplan, Bruce A. and Kukich, Karen and Lu, Chi and Rock, Donald A. and Wolff, Susanne}", Title="System and method for computer-based automatic essay scoring", Publisher="Educational Testing Service", Abstract="A method of grading an essay using an automated essay scoring system is provided. The method comprises the automated steps of (a) parsing the essay to produce parsed text, wherein the parsed text is a syntactic representation of the essay, (b) using the parsed text to create a vector of syntactic features derived from the essay, (c) using the parsed text to create a vector of rhetorical features derived from the essay, (d) creating a first score feature derived from the essay, (e) creating a second score feature derived from the essay, and (f) processing the vector of syntactic features, the vector of rhetorical features, the first score feature, and the second score feature to generate a score for the essay. The essay scoring system comprises a Syntactic Feature Analysis program which creates a vector of syntactic features of the electronic essay text, a Rhetorical Feature Analysis program which creates a vector of rhetorical features of the electronic essay text, an EssayContent program which creates a first Essay Score Feature, an ArgContent program which creates a second Essay Score Feature, and a scoring engine which generates a final score for the essay from the vector of syntactic features, the vector of rhetorical features, the first score feature, and the second score feature." Year=2002} @InProceedings{burstein-etal2001, Author="{Burstein, Jill C. and Kukich, Karen and Andreyev, Slava and Marcu, Daniel}", Title="{Towards automatic classification of discourse elements in essays}", Booktitle="Proceedings of 39th Annual Meeting of the Association for Computational Linguistics (ACL'01)", Address="Toulouse, France", Year=2001} @InProceedings{burstein-etal98, Author="{Burstein, Jill C. and Kukich, Karen and Wolfe, Susanne and Lu, Chi and Chodorow, Martin S.}", Title="{Enriching automated essay scoring using discourse marking}", Booktitle="Proceedings of 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (ACL-COLING'98) Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="15-21", Year=1998} @Article{burstein-marcu2003, Author="{Burstein, Jill C. and Marcu, Daniel}", Title="{A machine learning approach for identification of thesis and conclusion statements in student essays}", Journal="Computers and the Humanities", Volume=37, Number=4, Pages="455-467", Note="Cited Reference Count: 18 Cited References: BURSTEIN J, 2001, P 39 ANN M ASS COMP, P15 BURSTEIN J, 2003, ADV NATURAL LANGUAGE, V18, P32 BURSTEIN J, 2003, AUTOMATED ESSAY SCOR, P113 BURSTEIN J, 2003, AUTOMATED ESSAY SCOR, P209 BURSTEIN J, 2003, P 15 ANN C INN APPL BURSTEIN J, 1998, P WORKSH DISC REL DI, P90 BURSTEIN JC, 1998, P 36 ANN M ASS COMP, P206 ELLIOTT S, 2003, AUTOMATED ESSAY SCOR, P71 KRIPPENDORFF K, 1980, CONTENT ANAL INTRO I LANDAUER T, 2003, AUTOMATED ESSAY SCOR, P87 LARKEY L, 2003, AUTOMATED ESSAY SCOR, P55 LEACOCK C, 2003, AUTOMATED ESSAY SCOR, P195 MANN WC, 1988, TEXT, V8, P243 MARCU D, 2000, THEORY PRACTICE DISC PAGE EB, 2003, AUTOMATED ESSAY SCOR, P43 QUIRK R, 1985, COMPREHENSIVE GRAMMA SCARDAMALIA M, 1985, LIT LANGUAGE LEARNIN WHITE EM, 1994, TEACHING ASSESSING W, P103 Article", Abstract="This study describes and evaluates two essay-based discourse analysis systems that identify thesis and conclusion statements from student essays written on six different essay topics. Essays used to train and evaluate the systems were annotated by two human judges, according to a discourse annotation protocol. Using a machine learning approach, a number of discourse-related features were automatically extracted from a set of annotated training data. Using these features, two discourse analysis models were built using C5.0 with boosting: a topic-dependent and a topic-independent model. Both systems outperformed a positional algorithm. While the topic-dependent system showed somewhat higher performance, the topic-independent system showed similar results, indicating that a system can generalize to unseen data-that is, essay responses on topics that the system has not seen in training." Year=2003} @InProceedings{busch-review2005, Author="{Busch, Michael}", Title="Review of: Taboada, M. (2004) Building Coherence and Cohesion", Publisher="LINGUIST List 15.1688", Volume=2005, Number=May, Year=2005} @InProceedings{carbonel-etal2007, Author="{Carbonel, Thiago Ianez and Collovini, Sandra S. and Coelho, Jorge César and Fuchs, Juliana Thiesen and Rino, Lucia Helena Machado and Vieira, Renata}", Title="{Summ-it: Um corpus anotado com informações discursivas visando à sumarização automática}", Booktitle="Proceedings of XXVII Congresso da SBC: V Workshop em Tecnologia da Informação e da Linguagem Humana – TIL", Address="Rio de Janeiro, Brazil", Pages="1605-1614", Year=2007} @InProceedings{carbonel-etal2006, Author="{Carbonel, Thiago Ianez and Seno, E.R.M. and Pardo, Thiago Alexandre Salgueiro and Coelho, Jorge César and Collovini, Sandra S. and Rino, Lucia Helena Machado and Vieira, Renata}", Title="{A two-step summarizer of Brazilian Portuguese texts}", Booktitle="Proceedings of the 4th Workshop on Information and Human Language Technology (TIL)", Address="Ribeirão Preto-SP, Brazil", Year=2006} @Article{carenini93, Author="{Carenini, Giuseppe and Pianesi, Fabio and Ponzi, Marco and Stock, Oliviero}", Title="{Natural language generation and hypertext access}", Journal="Applied Artificial Intelligence", Volume=7, Number=2, Pages="135-164", Year=1993} @InProceedings{carenini90, Author="{Carenini, Giuseppe and Ponzi, Marco and Stock, Oliviero}", Title="{Combining natural language and hypermedia as new means for information access}", Booktitle="Proceedings of Fifth European Conference of Cognitive Ergonomics (ECCE '90)", Address="Urbino, Italy", Year=1990} @InProceedings{carlson-etal2001, Author="{Carlson, Lynn and Conroy, John and Marcu, Daniel and O'Leary, Dianne and Okurowski, Mary Ellen and Taylor, Anthony and Wong, William}", Title="{An empirical study of the relation between abstracts, extracts, and the discourse structure of texts}", Booktitle="Proceedings of Document Understanding Conference (DUC-2001)", Address="New Orleans, Louisiana", Year=2001} @InProceedings{carlson-marcu2001, Author="{Carlson, Lynn and Marcu, Daniel}", Title="Discourse Tagging Manual", Pages="87", Month="September 11, 2001", Abstract="The second version of the annotator's manual. Used in the construction of the LDC corpus. Includes instructions on segmentation, identification of cue phrases and related relations, and full relation definitions. Also includes instructions on using Marcu's annotation tool." Year=2001} @InProceedings{carlson-etal2001b, Author="{Carlson, Lynn and Marcu, Daniel and Okurowski, Mary Ellen}", Title="{Building a discourse tagged corpus in the framework of Rhetorical Structure Theory}", Booktitle="Proceedings of 2nd SIGDIAL Workshop on Discourse and Dialogue, Eurospeech 2001", Address="Aalborg, Denmark", Year=2001} @InProceedings{ldc-rst-corpus, Author="{Carlson, Lynn and Marcu, Daniel and Okurowski, Mary Ellen}", Title="RST Discourse Treebank, LDC2002T07", Publisher="Linguistic Data Consortium", Number=LDC2002T07, Year=2002} @InCollection{carlson-etal2003, Author="{Carlson, Lynn and Marcu, Daniel and Okurowski, Mary Ellen}", Title="{Building a discourse tagged corpus in the framework of Rhetorical Structure Theory}", BookTitle="Current and New Directions in Discourse and Dialogue", Editor="van Kuppevelt, Jan and Smith, Ronnie", Publisher="Springer", Address="Berlin", Pages="85-112", Abstract="Largely a reprint of the 2001 SIGDIAL paper, with more emphasis on potential use of the corpus." Year=2003} @Article{caro-bisseret97, Author="{Caro, S. and Bisseret, A.}", Title="{Using weakening paralinguistic organizers in electronic documents: an experimental approach}", Journal="Travail Humain", Volume=60, Number=4, Pages="409-437", Abstract="This paper deals with what are called here paralinguistic organizers i.e. textual devices like underlining, brackets, footnotes, and, on screen, pop upfields..., In the framework at he theory of discourse comprehension (Van Dijk & Kintsch, 1983) it is proposed to view technical texts as tools, more Or less efficient, that readers use to build their representation (situation model). it is known that the schematic superstructure of a text can significantly enhance its comprehension and memorization. It ir assumed here that another kind of text structure could play a similar role ie. the structure based on the main points/secondary points distinction. More generally a text can be viewed as a set of textual units, each one corresponding to a communicative intention of the writer In other terms, each textual unit has a propositionnal content and an illocutory value. The distinction of secondary points from the main points corresponds to a value of "importance minimization". Among secondary points, a number of more precise illocutory values can be found in technical texts such as commenting, illustrating, guiding the reading process, synthesizing... Our conjecture ii that a clear distinction by the reader of these illocutory values should contribute to text comprehension and memorization as well as information retrieval. Analyzing a corpus of various technical texts we built a typology of textual units on the basis of the writer' intentions. In order to test the cognitive reality of such a typology, subjects were requested to analyze texts dividing them into textual units and to categorize these units according to the typology, only opt the basis of language (the paralinguistic organizers were removed). The results showed that, except for subjects trained in text analysis (students in psycholinguistics), such a categorization was a difficult task. Paralinguistics organizers such as parenthesis, footnotes, and pop-up fields on screen, should play an important role signaling the writer's "minimization" intention when secondary points are concerned. In two experiments the effect of such paralinguistic organizers was studied Groups of subjects were requested to read the same text with and without organizers. The subjects had to read texts "from beginning to end" knowing that they would have to answer questions on the text The results did not confirm the common signification (minimization) of the studied organizers. Putting textual units in brackets or in footnotes did not decrease significantly their memorization; putting textual units in pop up fields increased their memorization. A final experiment investigated the role of pop up fields compared to brackets in an information retrieval task (in a small base of texts) as opposed to a a from beginning to ends reading task. The results showed that, in this kind of task, putting secondary pieces of information into pop up fields significantly speeded the search process compared to a condition in which the same information war displayed in brackets. In conclusion it is argued that selecting information is an important subprocess of text processing, even when reading from beginning to end. In parallel with the increasing production of electronic documents, research on typology of textuals units and on type-signaling devices is needed toward efficient "access structures" for technical texts." Year=1997} @InProceedings{cassell-etal2001, Author="{Cassell, Justine and Nakano, Yukiko and Bickmore, Timothy W. and Sidner, Candace L. and Rich, Charles}", Title="{Non-verbal cues for discourse structure}", Booktitle="Proceedings of the 41st Meeting of the Association for Computational Linguistics", Address="Toulouse, France", Pages="17-19", Year=2001} @InCollection{cawsey90, Author="{Cawsey, Alison}", Title="{Generating explanatory discourse}", BookTitle="Current Research in Natural Language Generation", Editor="Dale, Robert and Mellish, Chris and Zock, Michael", Publisher="Academic Press", Address="London", Pages="75-101", Abstract="Presents a system for the generation of interactive explanatory dialogue (human-computer) as opposed to simple text. Integrates theories of text structure, dialogue structure, and user modelling." Year=1990} @InProceedings{cawsey91, Author="{Cawsey, Alison}", Title="{Using plausible inference rules in description planning}", Booktitle="Proceedings of 5th Conference of the European Chapter of the Association for Computational Linguistics (EACL'91)", Address="Berlin, Germany", Pages="119-124", Year=1991} @Article{cawsey95, Author="{Cawsey, Alison}", Title="{Participating in Explanatory Dialogues - Interpreting and Responding to Questions in Context - Moore,Jd}", Journal="Computational Linguistics", Volume=21, Number=3, Pages="422-424", Note="Cited Reference Count: 4 Cited References: MANN WC, 1988, TEXT, V8, P243 MOORE JD, 1993, COMPUTATIONAL LINGUI, V19, P651 MOORE JD, 1995, PARTICIPATING EXPLAN SWARTOUT W, 1991, IEEE EXPERT, V6, P58 Book Review", Abstract="Book review", Year=1995} @InCollection{chafai-etal2006, Author="{Chafai, N. E. and Pelachaud, C. and Pele, D. and Breton, G.}", Title="{Gesture expressivity modulations in an ECA application}", BookTitle="Intelligent Virtual Agents, Proceedings", Series="Lecture Notes in Artificial Intelligence", Volume=4133, Pages="181-192", Abstract="In this paper, we propose a study of co-verbal gesture properties that could enhance the animation of an Embodied Conversational Agent and their communicative performances. This work is based on the analysis of gesture expressivity over time that we have study from a corpus of 2D animations. First results point out two types of modulations in gesture expressivity that are evaluated on their communicative performances. A model of these modulations is proposed." Year=2006} @InCollection{chafe-rst96, Author="{Chafe, Wallace}", Title="{Beyond beads on a string and branches on a tree}", BookTitle="Conceptual Structure, Discourse and Language", Editor="Goldberg, Adele E." Publisher="CSLI", Address="Stanford, CA", Pages="49-65", Year=1996} @Article{chafe2002, Author="{Chafe, Wallace}", Title="{Searching for meaning in language - A memoir}", Journal="Historiographia Linguistica", Volume=29, Number=1-2, Pages="245-261", Year=2002} @Article{chan2000, Author="{Chan, S. W. K.}", Title="{Using heterogeneous linguistic knowledge in local coherence identification for information retrieval}", Journal="Journal of Information Science", Volume=26, Number=5, Pages="313-328", Abstract="This paper proposes a novel approach to automatic text segmentation without a full semantic understanding. in order to analyse the linguistic bonds and determine the degree of coherence that a text may exhibit, the tremendous diversity of textual relations in a discourse network is represented. A corpus of mutual linguistic knowledge that captures the similarity of meaning and causal relations is encoded in the discourse network, which is then subjected to a cluster algorithm. As a result, segments in the text are segregated into clusters according to their textual similarity. Topic boundaries in a text can be identified by observing the shifts of segments from one cluster to another. The experimental results show that the combination of the heterogeneous knowledge is capable of addressing the topic shifts. Comparison with a related method demonstrates that the algorithm is closely related to the topic boundaries. Given the increasing recognition of text structure in the fields of information retrieval in unpartitioned text, this approach provides a quantitative model and an efficient tool in text segmentation." Year=2000} @Article{chan2004, Author="{Chan, S. W. K.}", Title="{Automatic discourse structure detection using shallow textual continuity}", Journal="International Journal of Human-Computer Studies", Volume=61, Number=1, Pages="138-164", Abstract="A shallow natural language processing approach to discourse structure detection based on the analysis of textual continuity is described. What distinguishes it from previous research is that it does not work toward on the discovery of the formal subtopic structures. In contrast, attention is focused in uncovering the main factors in textual continuity and simulating a dynamic detection mechanism of cohesive sentence-based fragments. A connectionist filtering algorithm is used to capture the textual continuity as one of the structural backbone of text. As a result, the content conveyed by text with discontinuous topic sequence is, on average, most unlikely to be included in the resultant discourse structure. A prototype and its evaluation with various statistics are included. (C) 2003 Elsevier Ltd. All rights reserved." Year=2004} @Article{chan2006, Author="{Chan, S. W. K.}", Title="{Beyond keyword and cue-phrase matching: A sentence-based abstraction technique for information extraction}", Journal="Decision Support Systems", Volume=42, Number=2, Pages="759-777", Abstract="With the explosion in the quantity of on-line text and multimedia information in recent years, there has been a renewed interest in the automated extraction of knowledge and information in various disciplines. In this paper, we provide a novel quantitative model for the creation of a summary by extracting a set of sentences that represent the most salient content of a text. The model is based on a shallow linguistic extraction technique. What distinguishes it from previous research is that it does not work on the detection of specific keywords or cue-phrases to evaluate the relevance of the sentence concerned. Instead, the attention is focused on the identification of the main factors in the textual continuity. Simulation experiments suggest that this technique is useful because it moves away from a purely keyword-based method of textual information extraction and its associated limitations. (c) 2005 Elsevier B.V. All rights reserved." Year=2006} @InProceedings{chan-etal2000, Author="{Chan, Samuel W. K. and Lai, Tom B. Y. and Gao, W. J. and T'sou, Benjamin K.}", Title="{Mining discourse markers for Chinese textual summarization}", BookTitle="Proceedings of the NAACL-ANLP Workshop on Automatic Text Summarization", Address="Seattle, WA", Pages="11-20", Year=2000} @InProceedings{cheng2000, Author="{Cheng, Hua}", Title="{Experimenting with the interaction between aggregation and text structuring}", Booktitle="Proceedings of ANLP-NAACL 2000 Student Research Workshop", Address="Seattle, Washington", Pages="1-6", Year=2000} @InProceedings{cheng-mellish2000, Author="{Cheng, Hua and Mellish, Chris}", Title="{Capturing the interaction between aggregation and text planning in two generation systems}", Booktitle="Proceedings of First International Conference on Natural Language Generation (INLG'00)", Address="Mitzpe Ramon, Israel", Pages="186-193", Year=2000} @InProceedings{chiarcos-krasavina-corpuslx2005, Author="{Chiarcos, Christian and Krasavina, Olga}", Title="{Rhetorical distance revisited: A pilot study}", Booktitle="Proceedings of Corpus Linguistics 2005", Address="Birmingham, UK", Year=2005} @InCollection{chiarcos-krasavina-constraints2008, Author="{Chiarcos, Christian and Krasavina, Olga}", Title="{Rhetorical distance revisited: A parametrized approach}", BookTitle="Constraints in Discourse", Editor="Benz, Anton and Kühnlein, Peter", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="97–115", Year=2008} @InCollection{chiarcos-stede2004, Author="{Chiarcos, Christian and Stede, Manfred}", Title="{Salience-driven text planning}", BookTitle="Natural Language Generation. Proceedings of the Third International Conference on Natural Language Generation", Publisher="Springer", Address="Berlin", Pages="21-30", Abstract="We present an algorithm for hierarchical text planning of paragraphs involving object descriptions, comparisons and recommendations. Building on previous work on bottom-up text planning and user-tailored text generation, we develop a numerical model of 'propositional salience' to capture both speaker's intentions and local coherence in a single framework for generating complex discourse structures." Year=2004} @PhDThesis{chotimongkol2008, Author="Chotimongkol, Ananlada", Title="{Learning the structure of task-oriented conversations from the corpus of in-domain dialogs}", School="Carnegie Mellon University", Note="Citation of Taboada and Mann 2006, part 1", Type="PhD dissertation", Year=2008} @InCollection{chuang-yang2000, Author="{Chuang, W. T. and Yang, J.}", Title="{Text summarization by sentence segment extraction using machine learning algorithms}", BookTitle="Knowledge Discovery and Data Mining, Proceedings", Series="Lecture Notes in Artificial Intelligence", Volume=1805, Pages="454-457", Abstract="We present an approach to the design of an automatic text summarizer that generates a summary by extracting sentence segments. First, sentences are broken into segments by special cue markers. Each segment is represented by a set of predefined features (e.g. location of the segment, number of title words in the segment). Then supervised learning algorithms are used to train the summarizer to extract important sentence segments, based on the feature vector. Results of experiments indicate that the performance of the proposed approach compares quite favorably with other approaches (including MS Word summarizer)." Year=2000} @Article{cornish89, Author="{Cornish, Francis}", Title="{Discourse structure and anaphora: Written and conversational English (review article)}", Journal="Lingua", Volume=79, Number=2-3, Pages="229-243", Note="Cited Reference Count: 13 Cited References: ARIEL M, 1988, J LINGUIST, V24, P65 BOSCH P, 1983, AGREEMENT ANAPHORA S CHAFE WL, 1980, PEAR STORIES CLANCY P, 1980, PEAR STORIES COGNITI, P127 CORNISH F, 1986, ANAPHORIC RELATIONS CORNISH F, 1988, J SEMANTICS, V5, P233 DUBOIS JW, 1980, PEAR STORIES COGNITI, P203 FOX BA, 1986, TEXT, V6, P25 GROSZ B, 1977, 5 STANF RES I TECHN MANN W, UNPUB RHETORICAL STR MANN WC, 1988, TEXT, V8, P243 REICHMAN R, 1981, 4681 REP SANFORD AJ, 1988, LANG SPEECH, V31, P43 Review", Year=1989} @Article{cornish-intro2009, Author="{Cornish, Francis}", Title="{Relations de cohérence et fonctionnement des anaphores (RCFA) (Présentation)}", Journal="Journal of French Language Studies", Volume=19, Number=2, Pages="151-157", Note="Citation of Taboada and Mann 2006, part 1", Year=2009} @Article{cornish2009, Author="{Cornish, Francis}", Title="{Le rôle des anaphores dans la mise en place des relations de cohérence dans le discours: l'hypothèse de J.R. Hobbs}", Journal="Journal of French Language Studies", Volume=19, Number=2, Pages="159-181", Note="Citation of Taboada 2006 (JPrags)", Year=2009} @InProceedings{corston-patent2000, Author="{Corston, Simon and de Campos, Miguel Cardoso}", Title="Automatically recognizing the discourse structure of a body of text", Publisher="Microsoft Corporation", Abstract="The present invention is directed to recognizing a discourse structure of a body of text. In a preferred embodiment, a discourse structure recognition facility utilizes syntactic information associated with the body of text to generate a discourse structure tree that characterizes the discourse structure of the body of text. The facility first identifies in the body of text a number of clauses. The facility then determines, for each distinct pair of clauses, which of a number of possible discourse relations should be hypothesized between the pair of clauses, based on the syntactic structure and semantic of the body of text relative to the pair of clauses. The facility then applies the hypothesized relations to the clauses in order to produce a discourse structure tree characterizing the discourse structure of the body of text. In certain embodiments, the facility further generates from the produced discourse structure tree a synopsis of the body of text reflecting the primary goals pursued by its author." Year=2000} @InProceedings{corston-oliver98-aaai, Author="{Corston-Oliver, Simon}", Title="{Beyond string matching and cue phrases: Improving efficiency and coverage in discourse analysis}", Booktitle="Proceedings of AAAI 1998 Spring Symposium Series, Intelligent Text Summarization", Address="Madison, Wisconsin", Pages="9-15", Year=1998} @InProceedings{corston-oliver98, Author="{Corston-Oliver, Simon}", Title="{Identifying the linguistic correlates of rhetorical relations}", Booktitle="Proceedings of the Workshop on Discourse Relations and Discourse Markers, COLING/ACL '98", Pages="8-14", Year=1998} @InProceedings{corston-oliver2000, Author="{Corston-Oliver, Simon}", Title="{Using decision trees to select the grammatical relation of a noun phrase}", Booktitle="Proceedings of 1st SIGdial Workshop on Discourse and Dialogue", Address="Hong Kong", Year=2000} @InProceedings{corston-oliver-dolan99, Author="{Corston-Oliver, Simon and Dolan, William B}", Title="{Less is more: Eliminating index terms from subordinate clauses}", Booktitle="Proceedings of 37th Annual Meeting of the Association for Computational Linguistics (ACL'99)", Address="College Park, Maryland", Pages="349-356", Year=1999} @InProceedings{cox-etal99, Author="{Cox, Richard and O'Donnell, Michael and Oberlander, Jon}", Title="{Dynamic versus static hyperedia in museum education: An evaluation of ILEX the Intelligent Labelling Explorer}", Booktitle="Proceedings of 9th International Conference on Artificial Intelligence in Education (AI-ED99)", Address="Le Mans, France", Pages="181-188", Year=1999} @InProceedings{creswell-etal2002, Author="{Creswell, Cassandre and Forbes, Katherine and Miltsakaki, Eleni and Prasad, Rashmi and Joshi, Aravind K. and Webber, Bonnie}", Title="{The discourse anaphoric properties of connectives}", Booktitle="Proceedings of 4th Discourse Anaphora and Anaphor Resolution Colloquium (DAARC)", Address="Lisbon, Portugal", Year=2002} @InProceedings{creswell-etal2003, Author="{Creswell, Cassandre and Forbes, Katherine and Miltsakaki, Eleni and Prasad, Rashmi and Joshi, Aravind K. and Webber, Bonnie}", Title="Penn Discourse Treebank: Building a Large Scale Annotated Corpus Encoding DLTAG-based Discourse Structure and Discourse Relations", Pages="8", Abstract="Outlines the plans, methodology, and applications of a DLTAG-pased Treebank. Also cites Marcu's corpus as the nearest thing out there, and notes important differences between RST and DLTAG", Year=2003} @InCollection{cristea2000, Author="{Cristea, Dan}", Title="{An incremental discourse parser architecture}", BookTitle="Natural Language Processing - NLP 2000: Second International Conference", Publisher="Springer", Address="Patras, Greece", Pages="162-175", Abstract="We present a discourse parsing architecture based on an incremental approach and aimed at building a rhetorical structure of a free text. Vein expressions computed on the developing structure help to restrict the domains of referential accessibility on which resolution of anaphora is performed. The parsing process is guided by cohesion and coherence constraints." Year=2000} @InCollection{cristea2003, Author="{Cristea, Dan}", Title="{The relationship between discourse structure and referentiality in Veins Theory}", BookTitle="Natural Language Processing between Linguistic Inquiry and System Engineering", Editor="Menzel, W. and Vertan, C." Publisher="A.I. Cuza University Publishing House", Address="Iasi, Romania", Year=2003} @InProceedings{cristea-motivations2005, Author="{Cristea, Dan}", Title="{Motivations and implications of Veins Theory}", Booktitle="Proceedings of the 2nd International Workshop on Natural Language Understanding and Cognitive Science", Address="Miami, FL", Pages="32-44", Year=2005} @Book{cristea-etal-proceed99, Author="{Cristea, Dan and Ide, Nancy and Marcu, Daniel}", Title="Proceedings of ACL Workshop on the Relation of Discourse/Dialogue Structure and Reference", Publisher="ACL", Address="College Park, MD", Year=1999} @InProceedings{cristea-etal2000, Author="{Cristea, Dan and Ide, Nancy and Marcu, Daniel and Tablan, Valentin}", Title="{Discourse structure and coreference: An empirical study}", Booktitle="The 18th International Conference on Computational Linguistics (COLING'00)", Address="Saarbrücken, Germany", Pages="208-214", Year=2000} @InProceedings{cristea-etal98, Author="{Cristea, Dan and Ide, Nancy and Romary, Laurent}", Title="{Veins Theory: A model of global discourse cohesion and coherence}", Booktitle="Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics (ACL-98/COLING-98)", Address="Montréal, Canada", Pages="281-285", Year=1998} @InCollection{cristea-etal2005, Author="{Cristea, Dan and Postolache, O. and Pistol, L.}", Title="{Summarisation through discourse structure}", BookTitle="Computational Linguistics and Intelligent Text Processing", Series="Lecture Notes in Computer Science", Volume=3406, Pages="632-644", Abstract="In this paper we describe a method to obtain summaries focussed on specific characters of a free text. Summaries are extracted from discourse structures which differ from RST structures by the fact that the trees are binary and lack relation names. The discourse tree structures are obtained by combining constraints given by cue-phrases (resembling Marcu's method) with constraints coming from the exploitation of cohesion and coherence properties of the discourse (as proved by Veins Theory). The architecture of a summarisation system is presented on which evaluations intended to evidence the contribution of each module in the final result are performed and discussed." Year=2005} @InProceedings{cristea-webber97, Author="{Cristea, Dan and Webber, Bonnie}", Title="{Expectations in incremental discourse processing}", Booktitle="Proceedings of 35th Annual Meeting of the Association for Computational Linguistics (ACL'97)", Address="Madrid, Spain", Pages="88-95", Year=1997} @PhDThesis{cui, Author="Cui, Songren", Title="{A Comparison of English and Chinese Expository Rhetorical Structures}", School="UCLA", Type="Master's thesis", Year=1986} @InProceedings{dahlgren98, Author="{Dahlgren, Kathleen}", Title="{Lexical marking and the recovery of discourse structure}", Booktitle="Proceedings of COLING-ACL Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="65-71", Year=1998} @InProceedings{dale91, Author="{Dale, Robert}", Title="{The role of punctuation in discourse structure}", Booktitle="Proceedings of AAAI Fall Symposium on Discourse Structure in Natural Language Understanding and Generation", Address="Asilomar, CA", Pages="13-14", Year=1991} @Book{dale-etal92, Editor="{Dale, Robert and Hovy, Eduard and Rösner, Dietmar and Stock, Oliviero}", Title="Aspects of Automated Natural Language Generation", Publisher="Springer", Address="Berlin", Year=1992} @Book{dale-etal90, Editor="{Dale, Robert and Mellish, Chris and Zock, Michael}", Title="Current Research in Natural Language Generation", Publisher="Academic Press", Address="London", Year=1990} @Article{dale-etal98, Author="{Dale, Robert and Oberlander, Jon and Milosavljevic, Maria and Knott, Alistair}", Title="{Integrating Natural Language Generation and Hypertext to produce dynamic documents}", Journal="Interacting with Computers", Volume=11, Number=2, Pages="109-135", Abstract="Introduces the concepts of hypertext and NLG, culminating in their merging into Dynamic Hypertext. Goes on to discuss ILEX, and PEBA-II, an interactive encyclopedia project." Year=1998} @Article{dalianis92, Author="{Dalianis, H.}", Title="{A Method for Validating a Conceptual-Model by Natural-Language Discourse Generation}", Journal="Lecture Notes in Computer Science", Volume=593, Pages="425-444", Abstract="The support systems for conceptual modeling of today lack natural language feedback. The paper argues for the need of natural language discourse for the validation of a conceptual model. Based on this conclusion a suggestion is made on a natural language discourse generation system as a validation tool and also as a support tool in simulating a conceptual model. Various appropriate natural language discourses are then proposed in the paper. To conclude the paper a support system based on the natural language generation techniques of today and on previous working systems constructed by the author is suggested." Year=1992} @Article{dalianis99, Author="{Dalianis, H.}", Title="{Aggregation in natural language generation}", Journal="Computational Intelligence", Volume=15, Number=4, Pages="384-414", Abstract="The content of real-world databases, knowledge bases, database models, and formal specifications is often highly redundant and needs to be aggregated before these representations can be successfully paraphrased into natural language. To generate natural language from these representations, a number of processes must be carried out, one of which is sentence planning where the task of aggregation is carried out. Aggregation, which has been called ellipsis or coordination in Linguistics, is the process that removes redundancies during generation of a natural language discourse, without losing any information. The article describes a set of corpus studies that focus on aggregation, provides a set of aggregation rules, and finally, shows how these rules are implemented in a couple of prototype systems. We develop further the concept of aggregation and discuss it in connection with the growing literature on the subject. This work offers a new tool for the sentence planning phase of natural language generation systems." Year=1999} @Article{danlos2006, Author="{Danlos, Laurence}", Title="{Capacité générative forte de RST, SDRT et des DAG de dépendances pour le discours}", Journal="Traitement Automatique des Langues", Volume=47, Number=2, Pages="169-198", Note="Citation of Taboada and Mann, both papers", Year=2006} @InProceedings{danlos2007, Author="{Danlos, Laurence}", Title="{D-STAG: un formalisme pour le discours basé sur les TAG synchrones}", Booktitle="Proceedings of Traitement Automatique des Langues Naturelles 2007", Address="Toulousse, France", Pages="389-398", Year=2007} @InCollection{danlos-upv2007, Author="{Danlos, Laurence}", Title="{D-STAG: A discourse formalism using synchronous TAG}", BookTitle="Language, Representation and Reasoning", Editor="Aunargue, Mixel and Korta, Kepa and Larrazabal, Jesús M." Publisher="University of the Basque Country Press", Address="Bilbao, Spain", Note="Citation to Taboada and Mann, part 1", Year=2007} @InProceedings{danlos-lapalme99, Author="{Danlos, Laurence and Lapalme, Guy}", Title="{What is a rhetorical relation? An experiment combining two text generators}", Booktitle="Proceedings of AISB Workshop on Reference Architecture and Data Standards for Natural Language Processing", Address="Edinburgh, UK", Pages="1-7", Year=1999} @InCollection{daradoumis, Author="{Daradoumis, Thanasis}", Title="{Towards a representation of the rhetorical structure of interrupted exchanges}", BookTitle="Trends in Natural Language Generation: An Artificial Intelligence Perspective", Editor="Adorni, Giovanni and Zock, Michael", Publisher="Springer", Address="Berlin", Pages="106-124", Abstract="A model of dynamic phenomena in dialogue, which marries RST with exchange models of dialogue (Berry, Jim Martin (1992)). The resulting model is called Dialogic Rhetorical Structure Theory (DRST). In this paper, the model is applied to modelling interruptions in tutorial dialogues. (Interruption: a move that does not comply with the intention of the previous move). Interesting approach, merits attention, but it might be RST-inspired rather than RST-based." Year=1996} @InCollection{dargnat2008, Author="{Dargnat, Mathilde}", Title="{Constructionnalité des parataxes conditionnelles}", BookTitle="Congrès Mondial de Linguistique Française - CMLF'08", Editor="Durand, Jacques and Habert, Benoît and Laks, Bernard", Publisher="Institut de Linguistique Française", Address="Paris", Note="Citation of Taboada and Mann 2006, part 1 and part 2", Year=2008} @InProceedings{daume-marcu2002, Author="{Daumé, Hal, III and Marcu, Daniel}", Title="{A noisy-channel model for document compression}", Booktitle="Proceedings of 40th Annual Meeting of the Association for Computational Linguistics (ACL'02)", Address="Philadelphia, Pennsylvania", Pages="449-456", Year=2002} @InProceedings{de-carolis98, Author="{de Carolis, Berardina}", Title="{Introducing reactivity in adaptive Hypertext generation}", Booktitle="Proceedings of 13th European Conference on Artificial Intelligence (ECAI'98)", Publisher="John Wiley and Sons", Address="Brighton, UK", Pages="682-683", Year=1998} @InProceedings{de-carolis99, Author="{de Carolis, Berardina}", Title="{Generating mixed-initiative Hypertexts: A reactive approach}", Booktitle="Proceedings of Intelligent User Interfaces (IUI'99)", Address="Los Angeles, California", Pages="71-78", Year=1999} @InProceedings{de-carolis-etal2000, Author="{de Carolis, Berardina and Pelachaud, Catherine and Poggi, Isabella}", Title="{Verbal and nonverbal discourse planning}", Booktitle="Proceedings of Fourth International Conference on Autonomous Agents, Workshop on Achieving Human-Like Behaviour in Interactive Animated Agents", Address="Barcelona, Spain", Year=2000} @Article{rosis-etal99, Author="{de Rosis, F. and Grasso, Floriana and Berry, D. C.}", Title="{Refining instructional text generation after evaluation}", Journal="Artificial Intelligence in Medicine", Volume=17, Number=1, Pages="1-36", Abstract="In this paper, we describe how user-adapted explanations about drug prescriptions can be generated from already existing data sources. We start by illustrating the two-step approach employed in the first version of the natural language generator and the limitations of generated texts, that we discovered through analytical and empirical evaluations. We claim that, although style refinement would be needed in these texts, particular care should be devoted to implementing some of the persuasion techniques that doctors employ in their explanations. This would require either thoroughly revising the text planning techniques employed or converting to a multistep generation architecture. We justify why we selected this second alternative and propose some heuristics to repair problems found in the first version of the generator. Some final considerations about the advantages of this approach and the possibility of generalizing it to other domains conclude the paper. (C) 1999 Elsevier Science B.V. All rights reserved." Year=1999} @InProceedings{desilva2005, Author="{De Silva, Nishadi}", Title="{A narrative approach to technical document construction}", Booktitle="Proceedings of PREP 2005", Address="Lancaster, United Kingdom", Year=2005} @PhDThesis{desilva-thesis2007, Author="De Silva, Nishadi", Title="{A Narrative-Based Collaborative Writing Tool for Constructing Coherent Technical Documents}", School="University of Southampton", Note="Citation of Taboada and Mann (both papers)", Type="Ph.D. dissertation", Year=2007} @InProceedings{desilva-henderson2005, Author="{De Silva, Nishadi and Henderson, Peter}", Title="{Computer support for narrative structures}", Booktitle="Proceedings of Computers and Writing 2005", Address="Stanford University, CA", Year=2005} @InProceedings{desilva-nishadi-iceis2005, Author="{De Silva, Nishadi and Henderson, Peter}", Title="{Narrative support for technical documents: Formalising Rhetorical Structure Theory}", Booktitle="Proceedings of International Conference on Enterprise Information Systems (ICEIS)", Address="Miami, Fl", Year=2005} @InProceedings{desilva-henderson-acm2007, Author="{De Silva, Nishadi and Henderson, Peter}", Title="{Narrative-based writing for coherent technical documents}", Booktitle="Proceedings of the 25th annual ACM international conference on Design of communication", Address="El Paso, TX", Pages="208-215", Year=2007} @InProceedings{desilva-skaf-molli2006, Author="{De Silva, Nishadi and Skaf-Molli, Hala}", Title="{Narratives to preserve coherence in collaborative writing}", Booktitle="Proceedings of The Eighth International Workshop on Collaborative Editing Systems", Address="Banff, Canada", Year=2006} @InProceedings{degand98, Author="{Degand, Liesbeth}", Title="{On classifying connectives and coherence relations}", Booktitle="Proceedings of COLING-ACL Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="29-35", Year=1998} @Article{degand2000, Author="{Degand, Liesbeth}", Title="{Causal connectives or causal prepositions? Discursive constraints}", Journal="Journal of Pragmatics", Volume=32, Number=6, Pages="687-707", Abstract="In this article, we draw a comparison between causal prepositions and causal connectives and present them as alternative realizations of the underlying causal situation. It is our aim to investigate under which constraints a language user tends to select either of both causal alternatives. It appeared from a quantitative corpus analysis that these constraints are primarily pragmatic in nature, since they have to do in the first place with the discourse domain and with the management of given/new information. This is also confirmed by an analysis of the grammatical and lexical constraints on causal prepositions and connectives. (C) 2000 Elsevier Science B.V. All rights reserved." Year=2000} @Article{degandetal99, Author="{Degand, Liesbeth and Lefévre, Nathalie and Bestgen, Yves}", Title="{The impact of connectives and anaphoric expressions on expository discourse comprehension}", Journal="Document Design", Volume=1, Number=1, Pages="39-51", Abstract="This study focuses on the impact of linguistic markers of coherence on the comprehension of expository discourse. The impact of such markers on comprehension (i.e. off-line) is a highly controversial topic in current studies, especially for connectives for which a facilitating as well as an interfering role has been demonstrated. As a matter of fact, it seems that connectives facilitate the comprehension process in that they improve the reading process, but that they do not increase comprehension of the text. It might even be possible that they ease the reading task in such a way that they provide the reader with the "impression" of having understood the text instead of a real understanding. -- The objective of the experiment was to test this far reaching hypothesis for the use of connectives in expository texts. We wanted to determine the impact of causal connectives such as because ('parce que') and so ('donc') on comprehension and on the feeling of understanding, contrasting it with the impact of anaphoric expressions. Contrary to previous results, our experiment shows that the presence of connectives actually improved comprehension while it did not have an impact on the feeling of understanding." Year=1999} @Article{degand-sanders2002, Author="{Degand, Liesbeth and Sanders, Ted}", Title="{The impact of relational markers on expository text comprehension in L1 and L2}", Journal="Reading and Writing", Volume=15, Number=7-8, Pages="739-758", Abstract="Abstract This article reports on an experiment investigating the impact of causal discourse markers (connectives and signaling phrases) on the comprehension of expository texts in L1 and L2. Although several psycholinguistic studies have investigated the impact of connectives and lexical markers of text structure on comprehension (i.e. off-line), there is no consensus on the exact effect of explicit discourse markers on text understanding; three different findings are reported in the literature: markers would have a facilitating effect, an interfering effect or no effect a tall. The first goal of this article is to clarify this problem of contradicting results by limiting the scope of the study to causal relations, and to one specific text type:expository texts. Furthermore, the naturalness of the experimental texts was controlled, readers did not need specific background knowledge to understand the texts and the experimental method consisted of open answer questioning. Our second goal is to investigate to what extent a supposed effect of linguistic marking depends on readers proficiency in a first or second language.The experiment consisted in the reading of short expository texts in two languages, Dutch and French, which both functioned as L1 and L2.The results indicate that readers benefit from the presence of causal relational markers both in L1 and in L2. Implications for (theories of) text processing are discussed, as well as for the further insights in reading comprehension in L1 and L2." Year=2002} @Article{delin-bateman2002, Author="{Delin, Judy and Bateman, John}", Title="{Describing and critiquing multimodal documents}", Journal="Document Design", Volume=3, Number=2, Pages="140-155", Year=2002} @InProceedings{delin-etal94, Author="{Delin, Judy and Hartley, Anthony and Paris, Cécile and Scott, Donia and Vander Linden, Keith}", Title="{Expressing procedural relationships in multilingual instructions}", Booktitle="Proceedings of 7th International Workshop on Natural Language Generation (IWNLG 7)", Address="Kennebunkport, Maine", Pages="61-70", Year=1994} @Article{delin-etal-langsciences96, Author="{Delin, Judy and Hartley, Anthony and Scott, Donia}", Title="{Towards a contrastive pragmatics: Syntactic choice in English and French instructions}", Journal="Language Sciences", Volume=18, Number=3-4, Pages="897-931", Year=1996} @InProceedings{delin-etal96, Author="{Delin, Judy and Scott, Donia and Hartley, Anthony}", Title="{Language-specific mappings from semantics to syntax}", Booktitle="Proceedings of 16th International Conference on Computational Linguistics (COLING'96)", Address="Copenhagen, Denmark", Pages="292-297", Year=1996} @PhDThesis{denouden-thesis2004, Author="den Ouden, Hanny", Title="{Prosodic Realizations of Text Structure}", School="University of Tilburg", Type="Ph.D. dissertation", Year=2004} @InProceedings{den-ouden-etal2002, Author="{den Ouden, Hanny and Noordman, Leo and Terken, Jacques}", Title="{The prosodic realization of organisational features of text}", Booktitle="Proceedings of Speech Prosody 2002", Address="Aix-en-Provence, France", Year=2002} @TechReport{den-ouden-etal98, Author="{den Ouden, Hanny and van Wijk, Carel and Terken, Jacques and Noordman, Leo}", Title="{Reliability of Discourse Structure Annotation}", Institution="IPO Center for Research on User-System Interaction, Technical University of Eindhoven", Number="33, Annual Progress Report", Month="." Year=1998} @InProceedings{dieugenio-etal97, Author="{Di Eugenio, Barbara and Moore, Johanna D and Paolucci, Massimo}", Title="{Learning features that predict cue usage}", Booktitle="Proceedings of 35th Annual Meeting of the Association for Computational Linguistics (ACL'97)", Address="Madrid, Spain", Pages="80-87", Year=1997} @InProceedings{dipper-stede2006, Author="{Dipper, Stefanie and Stede, Manfred}", Title="{Disambiguating potential connectives}", Booktitle="Proceedings of KONVENS-06", Pages="167-173", Year=2006} @Article{dobes-novak91, Author="{Dobes, Z. and Novak, H. J.}", Title="{From Knowledge Structures to Text Structures}", Journal="Lecture Notes in Artificial Intelligence", Volume=546, Pages="670-684", Year=1991} @PhDThesis{druon2000, Author="Druon, Sébastien", Title="{Projet du Taxonomie des Connecteurs du Français pour le Traitement Automatique: L'exemple des Consécutifs}", School="Université Michel de Montaigne", Type="Master's thesis", Abstract="A corpus analysis of French discourse connectives, leading to a typology, with the long term goal of applying the results to a text generator. Appendix includes a listing of French discourse markers." Year=2000} @PhDThesis{druon2001, Author="Druon, Sébastien", Title="{Approche Exploratoire de le Relation de Consequence: Description et Implementation}", School="Université Toulouse le Mirail", Type="Ph.D. dissertation", Abstract="In-depth study of the Conséquence relation, including a catalogue of all lexical and semantic markers, and the implementation of an automatic search algorithm." Year=2001} @InCollection{egg-redeker2008, Author="{Egg, Markus and Redeker, Gisela}", Title="{Underspecified discourse representation}", BookTitle="Constraints in Discourse", Editor="Benz, Anton and Kühnlein, Peter", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="117-138", Year=2008} @InProceedings{egg-redeker2010, Author="{Egg, Markus and Redeker, Gisela}", Title="{How complex is discourse structure?}", Booktitle="Proceedings of the 7th Language Resources and Evaluation Conference (LREC)", Address="Malta", Year=2010} @InProceedings{eklund-wille98, Author="{Eklund, Peter and Wille, Rudolf}", Title="{A multimodal approach to term extraction using a Rhetorical Structure Theory tagger and formal concept analysis}", Booktitle="Proceedings of Second International Conference on Co-operative Multimodal Communication: Theory and Applications", Address="Tilburg, Netherlands", Pages="171-175", Year=1998} @Article{elhadad95, Author="{Elhadad, Michael}", Title="{Using argumentation in text generation}", Journal="Journal of Pragmatics", Volume=24, Pages="189-220", Year=1995} @InCollection{elson2004, Author="{Elson, D. K.}", Title="{Categorization of narrative semantics for use in generative multidocument summarization}", BookTitle="Natural Language Generation: Proceedings", Series="Lecture Notes in Artificial Intelligence", Volume=3123, Pages="192-197", Abstract="The generative summarization of textual stories has been one of the goals of computational narratology since attempts at full semantic NLU in the '70s. Our NLP group has recently created several systems for multidocument news summarization, but using purely statistical methods. Between these poles, there may be an unexplored avenue where knowledge of story structure can give partial, yet useful semantic understanding to a news reader. Such knowledge can then lead to summaries more informed than those based on solely statistical means. This student paper represents work in progress on a two-module system: The first module categorizes news articles into their underlying dramatic structures; the second will attempt to use this understanding to create and execute a generative plan, concisely retelling the story to form a surface-level summary." Year=2004} @Article{endres-niggemeyer94, Author="{Endres-Niggemeyer, B.}", Title="{Summarizing Text for Intelligent Communication - Results of the Dagstuhl Seminar}", Journal="Knowledge Organization", Volume=21, Number=4, Pages="213-223", Abstract="As a result of the transition to full-text storage, multimedia and networking, information systems are becoming more efficient but at the same time more difficult to use in particular because users are confronted with information volumes that increasingly exceed individual processing capacities. Consequently, there is an increase in the demand for user aids such as summarising techniques. Against this background, the interdisciplinary Dagstuhl Seminar Summarising Text for Intelligent Communication, (Dec. 1993) outlined the academic state of the art with regard to summarising (abstracting) and proposed future directions for research and system development. Research is currently shifting its attention from text summarising to summarising states of affairs. Recycling solutions are put forward in order to satisfy short-term needs for summarisation products. In the medium and long term, it is necessary to devise concepts and methods of intelligent summarising which have a better formal and empirical grounding and a more modular organisation." Year=1994} @Article{endres-niggemeyer2000, Author="{Endres-Niggemeyer, B.}", Title="{SimSum: an empirically founded simulation of summarizing}", Journal="Information Processing and Management", Volume=36, Number=4, Pages="659-682", Abstract="SimSum (Simulation of Summarizing) simulates 20 real-world working steps of expert summarizers. It presents an empirically founded cognitive model of summarizing and demonstrates that human summarization strategies can be simulated. The cognitive model operationalizes the discourse processing model developed by Kintsch and van Dijk. Knowledge engineering followed the KADS approach, empirical modeling used methods of grounded theory development. The observed strategies of expert summarizers have given rise to cooperating object-oriented agents communicating through dedicated blackboards. Each agent is implemented as a CLOS object with an assigned actor at the multimedia user interface. The interface is realized with Macromedia Director. Communication between CLOS and Macromedia Director is mediated by Apple Events. According to the first evaluation results in an educational environment, SimSum transmits summarization know-how effectively. It is, however, not designed as a tutorial system and serves active and curious users best. We are starting its expansion to summarizing in the WWW. (C) 2000 Published by Elsevier Science Ltd. All rights reserved." Year=2000} @TechReport{fabricius-hansen-behrens2010, Author="{Fabricius-Hansen, Cathrine and Behrens, Bergljot}", Title="{Elaboration and related discourse relations viewed from an interlingual perspective}", Institution="University of Oslo", Number="13", Type="Reports of the project Languages in Contrast", Year=2001} @InCollection{favero-robin2001, Author="{Favero, E. L. and Robin, J.}", Title="{Using OLAP and data mining for content planning in natural language generation}", BookTitle="Natural Language Processing and Information Systems", Series="Lecture Notes in Computer Science", Volume=1959, Pages="164-175", Abstract="We present a new approach to content determination and discourse organization in Natural Language Generation (NLG). This approach relies on two decision-support oriented database technologies, OLAP and data mining, and it can be used for any NLG application involving the textual summarization of quantitative data. It improves on previous approaches to content planning for NLG in quantitative domains by providing: (1) application domain independence, (2) efficient, variable granularity insight search in high dimensionality data spaces, (3) automatic discovery of surprising, counter-intuitive data, and (4) tailoring of output text organization towards different, declaratively specified, analytical perspectives on the input data." Year=2001} @InCollection{fawcett-davies, Author="{Fawcett, Robin P. and Davies, Bethan L.}", Title="{Monologue as a turn in dialogue: Towards an integration of Exchange Structure and Rhetorical Structure Theory}", BookTitle="Aspects of Automated Language Generation", Editor="Dale, Robert and Hovy, Eduard and Rösner, Dietmar and Stock, Oliviero", Publisher="Springer", Address="Berlin", Pages="151-166", Abstract="Two types of structure in discourse: genre and exchange structure. The latter is embedded in the former. All discourse can be considered dialogue (and even multilogue), and monologue is simply an extended turn in dialogue. Slight modification to the RST graphical and notational representation. Nuclei and satellites are in constituency relations (nodes in a tree), but the dependency relationship is maintained (The notation is just like that used in syntax, where a PP can be sister to an N, but the PP acts as a modifier to the N). The model establishes a discourse grammar at the higher level of discourse (i.e., genres). Different genres, however, all make use of the same model of exchange, the systemic flowchart model. Patterns within the SFM have different probabilities, determined by the choice of genre. The paper provides a snapshot of the flowcharts used to model dialogue." Year=1992} @InCollection{fawcett-etal88, Author="{Fawcett, Robin P. and van der Mije, Anita and van Wissen, Carla}", Title="{Towards a systemic flowchart model for discourse structure}", BookTitle="New Developments in Systemic Linguistics. Volume 2: Theory and Applications", Editor="Fawcett, Robin P and Young, David J", Publisher="Pinter", Address="London", Pages="116-143", Abstract="A proposal for a dynamic model of exchange structure, in general terms a model for all discourse: "the present model assumes that monologue is just a special case of an extended turn in dialogue" (p. 176). It claims some similarities with RST (the quote above refers to the differences), but the only similarity is that both try to account for structure of discourse, one monologic, the other dialogic. Dialogue is modelled in flowchart relationships, which in turn contain system networks (following systemic functional grammar). Flowchart lines express syntagmatic relationships of sequence, and system networks express paradigmatic relations of choice." Year=1988} @Article{fellbaum-etal2006, Author="{Fellbaum, C. and Hahn, U. and Smith, B.}", Title="{Towards new information resources for public health - From WordNet to MedicalWordNet}", Journal="Journal of Biomedical Informatics", Volume=39, Number=3, Pages="321-332", Abstract="In the last two decades, WORDNET has evolved as the most comprehensive computational lexicon of general English. In this article, we discuss its potential for supporting the creation of an entirely new kind of information resource for public health, viz. MEDICALWORDNET. This resource is not to be conceived merely as a lexical extension of the original WORDNET to medical terminology; indeed, there is already a considerable degree of overlap between WORDNET and the vocabulary of medicine. Instead, we propose a new type of repository, consisting of three large collections of (1) medically relevant word forms, structured along the lines of the existing Princeton WORDNET; (2) medically validated propositions, referred to here as medical facts, which will constitute what we shall call MEDICALFACTNET; and (3) propositions reflecting laypersons' medical beliefs, which will constitute what we shall call the MEDICALBELIEFNET. We introduce a methodology for setting up the MEDICALWORDNET. We then turn to the discussion of research challenges that have to be met to build this new type of information resource. We build a database of sentences relevant to the medical domain. The sentences are generated from WordNet via its relations as well as from medical statements broken down into elementary propositions. Two subcorpora of sentences are distinguished, MedicalBeliefNet and MedicalFactNet. The former is rated for assent by laypersons; the latter for correctness by medical experts. The sentence corpora will be valuable for a variety of applications in information retrieval as well as in research in linguistics and psychology with respect to the study of expert and non-expert beliefs and their linguistic expressions. Our work has to meet several considerable challenges. These include accounting for the distinction between medical experts and laypersons, the social issues of expert-layperson communication in different media, the linguistic aspects of encoding medical knowledge, and the reliability, volume, and emergence of medical knowledge. The work described here has been tested in a small pilot experiment [39] and awaits large-scale implementation. (c) 2005 Elsevier Inc. All rights reserved." Year=2006} @Article{ferraresi2009, Author="{Ferraresi, Gisella}", Title="{Transformation in coherence strategies of the Germans on the example of adverb connectors}", Journal="Zeitschrift für Dialektologie und Linguistik", Volume=75, Number=2, Pages="133-157", Note="Citation of Taboada and Mann 2006, part 1", Abstract="This article discusses adverbial connectors first from a synchronic and then a diachronic perspective. The primary focus is on the various functions that such elements perform in different syntactic positions. These are dependent on (among other things) sentence type, due to the fact that adverbial connectors modalize the sentence they introduce. Adverbial connectors placed in the prefield following another constituent (Nacherstposition), for instance, mark a contrastive topic. An examination of German in earlier periods reveals that e.g. an adverb like allerdings appears in the prefield relatively recently. The function of contrastive topic marking was performed by adverbial connectors placed before other elements in the prefield (Vorerstposition). In contemporary German, this position serves to introduce or contrast utterances, which can contain different types of sentences." Year=2009} @InProceedings{fisher-etal94, Author="{Fischer, Marcus and Maier, Elisabeth and Stein, Adelheit}", Title="{Generating cooperative system responses in information retrieval dialogues}", Booktitle="Proceedings of 7th International Workshop on Natural Language Generation (IWNLG 7)", Address="Kennebunkport, Maine", Pages="207-216", Year=1994} @InProceedings{forbes-etal2001, Author="{Forbes, Katherine and Miltsakaki, Eleni and Prasad, Rashmi and Sarkar, Anoop and Joshi, Aravind K. and Webber, Bonnie}", Title="{D-LTAG system - Discourse parsing with a lexicalised Tree Adjoining Grammar}", Booktitle="Proceedings of ESSLLI 2001 Workshop on Information Structure, Discourse Structure and Discourse Semantics", Address="Helsinki, Finland", Year=2001} @InProceedings{forbes-webber2002, Author="{Forbes, Katherine and Webber, Bonnie}", Title="{A semantic account of adverbials as discourse connectives}", Booktitle="Proceedings of 3rd SIGDial Workshop on Discourse and Dialogue", Address="Philadelphia, Pennsylvania", Year=2002} @InProceedings{foster2009, Author="{Foster, Robert}", Title="{Improving the output from software that generates multiple choice question (MCQ) test items automatically using Controlled Rhetorical Structure Theory}", Booktitle="Proceedings of the 7th International Conference on Recent Advances in Natural Language Processing", Address="Borovets, Bulgaria", Year=2009} @Book{fox87, Author="{Fox, Barbara A.}", Title="Discourse Structure and Anaphora: Written and Conversational English", Publisher="Cambridge University Press", Address="Cambridge", Abstract="Chapter 3: Anaphora in conversational English. She identifies two modes of description: (1) the context-determines-use mode; (2) the use-accomplishes-context mode. She describes the basic pattern of anaphora: (1) the fist mention of a referent in a sequence is done with a full NP; (2) after the first mention of a referent, a pronoun is used to display an understanding of the sequence as not yet closed; (3) a full NP is used to display an understanding of the preceding sequence containing other mentions of the same referent as closed. Pronouns are used to display that a sequence is not closed: in the middle of an adjacency pair, in a turn expansion, beyond adjacency pairs: an adjacency pair can be tied to a preceding pair (series, post-elaboration, return pop). Pronouns used to re-open a sequence: an instance of use-determines-context mode, in which the speaker accomplishes a reopening of the relevant sequence by using a pronominal form (40). Full NPs used to display that a sequence is understood as closed Anaphora in the environment of different gender referents: "the appearance of a different-gender referent does not alter the basic pattern of pronominalization established for the situation in which no "interfering" referents are mentioned." (48) Anaphora in the environment of same gender referents: "the simple introduction of another referent does not necessarily produce ambiguity; it is the structural organization of the talk that determines what will count as interfering and what not." (48) Full NPs used when other linguistic devices are not used: pronominalization is possible in the environment of same-gender referents if other linguistic devices besides the anaphor itself are used to guide the recipient to the intended referent. When other devices are not available or not used, full NPs will be used (58). Non-structural factors in anaphora: Disagreements, know + NP: overt recognitionals, assessments (negative), first mentions, demarcating a new unit, replacing an action, using the same anaphoric devices, switching perspective." Year=1987} @Article{fraser99, Author="{Fraser, Bruce}", Title="{What are discourse markers?}", Journal="Journal of Pragmatics", Volume=31, Number=7, Pages="931-952", Abstract="This paper is an attempt to clarify the status of discourse markers. These lexical expressions have been studied under various labels, including discourse markers, discourse connectives, discourse operators, pragmatic connectives, sentence connectives, and cue phrases. Although most researchers agree that they are expressions which relate discourse segments, there is no agreement on how they are to be defined or how they function. After reviewing prior theoretical research, I define discourse markers as a class of lexical expressions drawn primarily from the syntactic classes of conjunctions, adverbs, and prepositional phrases. With certain exceptions, they signal a relationship between the interpretation of the segment they introduce, S2, and the prior segment, Si. They have a core meaning, which is procedural, not conceptual, and their more specific interpretation is 'negotiated' by the context, both linguistic and conceptual. There are two types: those that relate the explicit interpretation conveyed by S2 with some aspect associated with the segment, S1; and those that relate the topic of S2 to that of S1. I conclude by presenting what appears to be the major classes according to their function. (C) 1999 Elsevier Science B.V. All rights reserved." Year=1999} @TechReport{fuchs2008, Author="{Fuchs, Juliana Thiesen}", Title="{Summ-it: Relatório de Anotação RST}", Institution="Série de Relatórios Técnicos do NILC", Type="Technical Report NILC-TR-08-02", Abstract="RESUMO: Neste relatório técnico, é apresentada a tarefa de anotação de parte do corpus Summit (corpus de textos jornalísticos de divulgação científica) segundo a RST – Rhetorical Structure Theory. É relatado todo o processo de anotação, desde a segmentação até a escolha de relações e a estruturação dos textos. Em cada etapa da tarefa de anotação relatada – segmentação, escolha de relações e estruturação –, são apresentados os resultados obtidos, enfatizando-se os padrões de organização retórica que podem ser observados nos textos. Além disso, são discutidos casos específicos que, afastando-se desses padrões, indicam as especificidades do corpus ou as limitações da análise realizada. Ao final do relatório, são anexadas tabelas e listas com dados estatísticos que permitem verificar a ocorrência e a representatividade das relações RST no corpus anotado." Year=2008} @Article{fuchs-giering2008, Author="{Fuchs, Juliana Thiesen and Giering, Maria Eduarda}", Title="{A importância da consideração de aspectos funcionais do texto para a eficiência de análises RST}", Journal="Revista Intercâmbio", Volume=XVII, Pages="in press", Abstract="RESUMO: Este artigo aborda a possibilidade de prever probabilisticamente como artigos jornalísticos de divulgação científica são organizados macro e microestruturalmente. Investiga-se em que medida é possível tratar da configuração prototípica microestrutural de artigos DC. Parte-se da noção de que a microestrutura de um texto depende funcionalmente de sua macroestrutura. Para a análise de exemplares do tipo textual em questão, é utilizado o modelo de relações elaborado pela RST – Rhetorical Structure Theory. PALAVRAS-CHAVE: configuração prototípica; microestrutura; macroesturtura; RST; artigo de divulgação científica. ABSTRACT: This article approaches the possibility of probabilistically foresee how science journalism texts are macro and micro-structurally organized. We investigate how it is possible to study the micro-structural prototypical configuration of science journalism texts. We start from the notion that the microstructure of a text functionally depends on its macrostructure. For the analysis of exemplars of the textual type considered here, we use the relation model developed by RST - Rhetorical Structure Theory. KEYWORDS: prototypical configuration; micro-structure; macro-structure; RST; science journalism text." Year=2008} @InProceedings{fukumoto-tsujii94, Author="{Fukumoto, Jun'ichi and Tsujii, Jun'ichi}", Title="{Breaking down rhetorical relations for the purpose of analysing discourse structures}", Booktitle="Proceedings of 15th International Conference on Computational Linguistics", Address="Kyoto, Japan", Pages="1177-1183", Year=1994} @Book{fuller59, Author="{Fuller, Daniel P.}", Title="The Inductive Method of Bible Study", Publisher="Fuller Theological Seminary", Address="Pasadena", Year=1959} @InCollection{furtado-ciarlini2001, Author="{Furtado, A. L. and Ciarlini, A. E. M.}", Title="{Generating narratives from plots using schema information}", BookTitle="Natural Language Processing and Information Systems", Series="Lecture Notes in Computer Science", Volume=1959, Pages="17-29", Abstract="The temporal dimension adds to databases the capability of functioning as repositories of narratives about the objects involved. Database narratives correspond both to sequences of past events and to simulated future events. This work addresses the problem of displaying such narratives in natural language. We focus here on the first kind of narrative, that is, we analyze a segment extracted from a log of the execution of pre-defined application-oriented operations, which is treated as a plot of the narrative in question. The main point in the presentation is that a three-level conceptual schema of the database provides a sound basis for interpreting such plots, although it should be complemented with further linguistic processing for the sake of fluency and conciseness. The schema-driven method for generating narratives from plots is described. A prototype Prolog implementation of the method is operational. A simple example is used to illustrate the discussion." Year=2001} @Article{furugori-etal2003, Author="{Furugori, T. and Lin, R. and Ito, T. and Han, D.}", Title="{Information extraction and summarization for newspaper articles on sassho-jiken}", Journal="Ieice Transactions on Information and Systems", Volume=E86D, Number=9, Pages="1728-1735", Abstract="Described here is an automatic text summarization system for Japanese newspaper articles on sassho-jiken (murders and bodily harms). We extract the pieces of information from a text, inter-connect them to represent the scenes and participants involved in the sassho-jiken, and finally produce a summary by generating sentences from the information extracted. An experiment and its evaluation show that, while a limitation being imposed on the domain, our method works well in depicting important information from the newspaper articles and the summaries produced are better in adequacy and readability than those obtained by extracting sentences." Year=2003} @Article{gallardo2005, Author="{Gallardo, S.}", Title="{Pragmatic support of medical recommendations in popularized texts}", Journal="Journal of Pragmatics", Volume=37, Number=6, Pages="813-835", Abstract="In order to be successful, speech acts that are intended to get the hearer to do something are often accompanied by supporting utterances aimed at making him/her understand their communicative purpose and, accept it as appropriate, as well as enabling him/her to perform the requested action. The purpose of this article is to determine the type of utterances that support recommendations in a corpus of popularizing medical texts published in two major Argentinean newspapers. The analysis shows that the most frequent supporting functions are those aimed at the acceptance of the communicative purpose. Also, supporting functions have been analyzed in terms of the speakers' acceptance of responsibility, i.e., we have considered whether supporting functions are (re)-formulated as a direct or indirect quotation of the information source or are formulated by the reporter. Findings show that a high percentage of supporting functions that justify recommendations are formulated as a direct quotation of the specialist's voice. (C) 2004 Elsevier B.V. All rights reserved." Year=2005} @Article{garcea-bazzanella99, Author="{Garcea, A. and Bazzanella, C.}", Title="{Textual links and the functions of discourse particles in Aulus Gellius's 'Noctes atticae'}", Journal="Lingua E Stile", Volume=34, Number=3, Pages="403-430", Abstract="A prototype taxonomic model will be applied to Aulus Gellius' Noctes Atticae, a miscellaneous work of the 2nd century, in order to analyze more effectively the specific features of a polymorphic text which is not adequately covered by traditional classifications. Gellius' relationship with his sources is in fact dynamic, based not on mimetic intentions but on a blend of different kinds of report and on different text parts, namely incipit, quotation, commentary, narration, and dialogue. The close relationship between text types and linguistic devices is investigated as a recursive feature, by focusing on discourse particles, which both indicate the interactional development and impose an internal textual hierarchy. Nam and sed perform a significant function in the commentaries and in several short chapters of Noctes Atticae, and in this function they cannot be replaced by other coniunctiones which belong to the same class in the normative Latin grammars (respectively, nam and enim to the causal, and at, autem, sed to the adversative). Discourse particles seem to reflect the nature of the text: while in the narrative structure discourse particles do not occur, in the incipit and quotations metatextual discourse particles prevail; in commentaries and dialogues interactional discourse particles signal both agreement and disagreement." Year=1999} @Article{garrido2005, Author="{Garrido Medina, Joaquín}", Title="{La persuasión en las cartas al director: Estructura de discurso, proceso de resumen y evaluación de estructuras retóricas}", Journal="Llengua Societat i Comunicació", Volume=3, Pages="31-46", Note="Citation of book", Abstract="Para explicar cómo ocurre la persuasión se pueden observar las relaciones entre unas oraciones y otras en los textos. Estas relaciones son retóricas en el sentido de que proporcionan pruebas que hacen más creíble lo que se afirma, dan información adicional para que se entienda mejor, etc. Los ejemplos de persuasión que se analizan son dos cartas al director que tratan de temas lingüísticos, una de la necesidad de correctores y otra del gasto de traducir de unas lenguas a otras en las instituciones europeas. La estructura de discurso que construyen estas relaciones permite distinguir la información más importante, y por tanto permite resumir, y hace posible evaluar la persuasión según las estrategias de sanción, emoción o razón." Year=2005} @PhDThesis{gawryjolek2009, Author="Gawryjolek, Jakub J." Title="{Automated annotation and visualization of rhetorical figures}", School="University of Waterloo", Note="Citation of Taboada and Mann 2006, part 1", Type="Master's thesis", Year=2009} @InProceedings{georg-etal2009, Author="{Georg, Gersende and Hernault, Hugo and Cavazza, Marc and Prendiger, Helmut and Ishizuka, Mitsuru}", Title="{From rhetorical structures to document structure: Shallow pragmatic analysis for document engineering}", Booktitle="Proceedings of the 9th ACM Symposium on Document Engineering", Address="Munich, Germany", Pages="185-192", Year=2009} @InProceedings{georg-etal-aime2009, Author="{Georg, Gersende and Hernault, Hugo and Cavazza, Marc and Prendiger, Helmut and Ishizuka, Mitsuru}", Title="{Analysing clinical guidelines' content with deontic and rhetorical structures}", Booktitle="Proceedings of the 12th Conference on Artificial Intelligence in Medicine", Address="Verona, Italy", Pages="86-90", Year=2009} @InProceedings{ghorbel-etal2001, Author="{Ghorbel, Hatem and Ballim, Azfal and Coray, Giovanni}", Title="{ROSETTA: Rhetorical and Semantic Environment for Text Alignment}", Booktitle="Proceedings of Corpus Linguistics 2001", Address="Lancaster, UK", Pages="224-233", Year=2001} @Article{giering2007, Author="{Giering, Maria Eduarda}", Title="{Organização retórica do artigo de opinião autoral: configuração prototípica}", Journal="Circulo de Lingüística Aplicada a la Comunicación", Volume=29, Pages="3-21", Abstract="RESUMO: Discutem-se resultados de pesquisa que investigou a distribuição probabilística das relações retóricas de 150 artigos de opinião autorais retirados de jornais brasileiros, observando a ocorrência de vias de continuidade e de relações que se estabelecem entre níveis de informação. Adotou-se proposta de E. Bernárdez, que vincula o modelo RST (Rhetorical Structure Theory) à idéia de que a organização textual pode ser entendida como uma série de vias de continuidade, etiquetadas com as relações da RST. Verificou-se que a distribuição de vias e de relações segue critérios probabilísticos; os artigos de opinião têm configuração prototípica, em termos de sua organização retórica macroestrutural, em vista da maior probabilidade de ocorrerem determinadas vias e relações e de nenhuma probabilidade de determinadas relações acontecerem; as escolhas estratégicas do produtor podem ser consideradas como ações para assegurar o fim comunicativo do artigo de opinião no contexto prototípico do jornal. PALAVRAS-CHAVE: texto, sistema, retórica, distribuição probabilística, prototipicidade. ABSTRACT: Results from a research that investigated the probabilistic distribution of rhetorical relations of 150 authorial opinion articles taken from Brazilian newspapers are discussed here, considering the occurrence of continuity means and the relations established among levels of information. Enrique Bernárdez¿ proposal, which links the RST model (Rhetorical Structure Theory) to the idea that the textual organization can be understood as a series of continuity means, labeled with the RST relations, was used to carry out this study. It was verified that the distribution of means and relations follows probabilistic criteria; the opinion articles have a prototypical configuration, considering their macro-structural rhetorical organization, noticed through the higher probability of occurring certain means and relations rather than other ones, which have zero probability of occurring; the producer strategic choices can be seen as actions to ensure the communicative end of the opinion article in the prototypical context of the newspaper. KEYWORDS: text, system, rhetoric, probabilistic distribution, prototypicity." Year=2007} @Article{giering2-2007, Author="{Giering, Maria Eduarda}", Title="{O texto como sistema aberto e a configuração prototípica de artigos de opinião autorais}", Journal="Linguagem em (Dis)curso", Volume=7, Number=1, Pages="27-44", Abstract="RESUMO: Discutem-se resultados de uma pesquisa que investigou a distribuição probabilística das relações retóricas de 150 artigos de opinião autorais retirados de jornais brasileiros, observando a ocorrência de vias de continuidade e de relações que se estabelecem entre níveis de informação. Adotou-se a proposta de E. Bernárdez, que vincula o modelo RST (Rhetorical Structure Theory) à idéia de que a organização textual pode ser entendida como uma série de vias de continuidade, etiquetadas com as relações da RST. Verificou-se que a distribuição de vias e de relações segue critérios probabilísticos; os artigos de opinião têm configuração prototípica, em termos de sua organização retórica macroestrutural, em vista da maior probabilidade de ocorrerem determinadas vias e relações e de nenhuma probabilidade de determinadas relações acontecerem; as escolhas estratégicas do produtor podem ser consideradas como ações para assegurar o fim comunicativo do artigo de opinião no contexto prototípico do jornal. PALAVRAS-CHAVE: texto; sistema; retórica; distribuição probabilística; prototipicidade. TITLE: The Text as an Open System and the Prototypical Configuration of Authorial Opinion Articles AUTHOR: Maria Eduarda Giering ABSTRACT: Results from a research that investigated the probabilistic distribution of rhetorical relations of 150 authorial opinion articles, taken from Brazilian newspapers, are discussed here, considering the occurrence of continuity means and the relations established among levels of information. Enrique Bernárdez' proposal, which links the RST model (Rhetorical Structure Theory) to the idea that the textual organization can be understood as a series of continuity means, labeled with the RST relations, was used to carry out this study. It was verified that the distribution of means and relations follows probabilistic criteria; the opinion articles have a prototypical configuration, considering their macro-structural rhetorical organization, noticed through the higher probability of the occurrence of certain means and relations rather than others, which have zero probability of occurrence; the producer's strategic choices can be seen as actions to ensure the communicative goal of the opinion article in the prototypical context of the newspaper. KEYWORDS: text; system; rhetoric; probabilistic distribution; prototypicity." Year=2007} @InCollection{gil-ratnakar2002, Author="{Gil, Y. and Ratnakar, V.}", Title="{TRELLIS: An interactive tool for capturing information analysis and decision making}", BookTitle="Knowledge Engineering and Knowledge Management, Proceedings", Series="Lecture Notes in Artificial Intelligence", Pages="37-42", Note="Cited Reference Count: 17 Cited References: ACKERMAN MS, 1996, P CSCW 96 ALLEN JF, 1984, ARTIFICIAL INTELLIGE, V23 COWIE J, 1996, COMMUN ACM, V39, P80 CROFT WB, 1999, ADV INFORMATION RETR GIL Y, 2002, P 1 INT SEM WEB C SA GRUBER TR, 1991, P 2 INT C PRINC KNOW KOIVUNEN MR, 2001, P K CAP 2001 WORKSH LAWRENCE JD, 2001, P 1 INT C KNOWL CAPT LEMMON E, 1977, INTRO MODAL LOGIC MANN WC, 1988, TEXT, V8 NAGAO K, 2001, IEEE MULTIMEDIA, V8, P69 POLLOCK JL, 1994, ARTIF INTELL, V67, P377 RADEV D, 1998, COMPUTATIONAL LINGUI SHUM SB, 1996, ENCY COMPUTER SCI TE SHUM SB, 2000, J DIGITAL LIB, V3 SMITH R, 2000, AI MAGAZINE FAL WILKINS DE, 1995, J LOGIC COMPUT, V5, P731 Article Volume 2473 in Lecture Notes in AI", Abstract="TRELLIS provides an interactive environment that allows users to add their observations, opinions, and conclusions as they analyze information by making semantic annotations about on-line documents. TRELLIS includes a vocabulary and markup language for semantic annotations of decisions and tradeoffs, and allows users to extend this vocabulary with domain specific terms or constructs that are useful to their particular task. To date, we have used TRELLIS with a variety of scenarios to annotate tradeoffs and decisions (e.g., military planning), organize materials (e.g., search results), analyze disagreements and controversies on a topic (e.g., intelligence analysis), and handle incomplete and conflicting information (e.g., genealogy research)." Year=2002} @Article{glanzberg2002, Author="{Glanzberg, M.}", Title="{Context and discourse}", Journal="Mind & Language", Volume=17, Number=4, Pages="333-375", Abstract="Current theories of context see context as composed of information that is localizable to individual utterances. Current theories of discourse grant that discourses have important global properties that are not so localizable. In this paper, I argue that context, even narrowly construed as whatever combine, with a sentence to determine truth conditions, must have a discourse-global component. I identify a context-dependence phenomenon related to the linguistic concepts of topic in focus, isolate the pertinent feature of context, and show that this Feature must be discourse-global in nature. I thus argue that context is as complicated as in entire discourse." Year=2002} @InCollection{gomez-gonzalez-taboada, Author="{Gómez-González, María de los Ángeles and Taboada, Maite}", Title="{Coherence relations in Functional Discourse Grammar}", BookTitle="Studies in Functional Discourse Grammar", Editor="Mackenzie, J. Lachlan and Gómez-González, María de los Ángeles", Publisher="Peter Lang", Address="Berne", Pages="227-259", Year=2005} @Article{gonzalez2005, Author="{González, Montserrat}", Title="{Pragmatic markers and discourse coherence relations in English and Catalan oral narrative}", Journal="Discourse Studies", Volume=7, Number=1, Pages="53-86", Abstract="This article explores the role that markers play in the pragmatic discourse structure of Catalan and English oral narratives. It is argued that their meaning is directly related to the sort of coherence relation that they establish with preceding and following propositions and discourse segments. centring the discussion on four discourse structures/components: ideational. rhetorical, sequential and inferential. The aim is to show the textual form-pragmatic function relationship by means of specific lexical units placed at specific parts of the narrative. The hypothesis held in this article is that pragmatic markers help in the organization of narrative Segments and that their semanticopragmatic traits make them appropriate for their use in specific segments." Year=2005} @Article{gonzalez-melon2006, Author="{González Melón, Eva}", Title="{Review of: Taboada, M. (2004) Building Coherence and Cohesion}", Journal="ITL, International Journal of Applied Linguistics", Volume=151, Pages="119-122", Year=2006} @Article{goutsos96, Author="{Goutsos, Dionysis}", Title="{A model of sequential relations in expository text}", Journal="Text", Volume=16, Number=4, Pages="501-533", Abstract="Aims at developing a model for describing the linear segmentation of discourse. Sequential relations are argued to be interactive with, but independent from ideational, interpersonal, and textual relations. RST is not used explicitly, but some RST relations are classified as sequential." Year=1996} @Article{grabski-stede2006, Author="{Grabski, M. and Stede, M.}", Title="{Bei: Intraclausal coherence relations illustrated with a German preposition}", Journal="Discourse Processes", Volume=41, Number=2, Pages="195-219", Abstract="Coherence relations are typically taken to link two clauses or larger units and to be signaled at the text surface by conjunctions and certain adverbials. Relations, however, also can hold within clauses, indicated by prepositions like despite, due to, or in case of, when these have an internal argument denoting an eventuality. Although these prepositions act as reliable cues to indicate a specific relation, others are lexically more neutral. We investigated this situation for the German preposition bei, which turns out to be highly ambiguous. We demonstrate the range of readings in a corpus study, proposing 6 more specific prepositions as a comprehensive substitution set. All these uses of bei share a common kernel meaning, which is missed by the standard accounts that assume lexical polysemy. We examine the range of coherence relations that can be signaled by bei and provide some factors here supporting the disambiguation task in a framework of discourse interpretation." Year=2006} @InProceedings{granville90, Author="{Granville, Robert Alan}", Title="{The role of underlying structure in text generation}", Booktitle="Proceedings of International Workshop on Natural Language Generation", Address="Dawson, Pennsylvania", Pages="105-111", Year=1990} @InProceedings{granville93, Author="{Granville, Robert Alan}", Title="{An algorithm for high-level organization of multi-paragraph texts}", Booktitle="Proceedings of ACL Workshop on Intentionality and Structure in Discourse Relations", Address="Columbus, Ohio", Pages="19-22", Year=1993} @InProceedings{grasso99, Author="{Grasso, Floriana}", Title="{Playing with RST: Two algorithms for the automated manipulation of discourse trees}", Booktitle="Proceedings of Text, Speech and Dialoge 2nd International Workshop", Address="Plzen, Czech Republic", Pages="357-360", Year=1999} @InProceedings{grasso2002, Author="{Grasso, Floriana}", Title="{Towards a framework for rhetorical argumentation}", Booktitle="Proceedings of the 6th Workshop on the Semantics and Pragmatics of Dialogue (EDILOG-2002)", Address="Edinburgh, UK", Pages="53-60", Year=2002} @Article{grasso-journal2002, Author="{Grasso, Floriana}", Title="{Towards computational rhetoric}", Journal="Informal Logic", Volume=22, Number=3, Pages="195-229", Year=2002} @InCollection{grasso2003, Author="{Grasso, Floriana}", Title="{Rhetorical coding of health promotion dialogues}", BookTitle="Artificial Intelligence in Medicine, Proceedings of the 9th Conference on Artificial Intelligence in Medicine in Europe, AIME 2003", Editor="Dojat, Michel and Keravnou, Elpida and Barahona, Pedro", Series="Lecture Notes in Artificial Intelligence 2780", Publisher="Springer", Address="Berlin", Pages="179-188", Note="Cited Reference Count: 25 Cited References: BARRIE K, 1991, COUNSELLING PROBLEM CARENINI G, 2002, P ECAI 2002 WORKSH C CARLETTA J, 1996, COMPUT LINGUIST, V22, P249 CARLETTA J, 1997, COMPUT LINGUIST, V23, P13 CAWSEY A, 1996, P ECAI 96 WORKSH GAP, P19 CAWSEY A, 1999, LECT NOTES ARTIF INT, V1620, P379 COHEN PR, 1990, INTENTIONS COMMUNICA, P221 CORE M, 1997, AAAI FALL S COMM ACT FOX J, 2000, SAFE SOUND ARTIFICIA FRIES E, 1993, J AM DIET ASSOC, V93, P551 GRASSO F, 2000, INT J HUM-COMPUT ST, V53, P1077 GRASSO F, 2002, EDILOG 02 P 6 WORKSH, P53 HORN PW, 1999, LNAI, V1620 MANN WC, 1988, TEXT, V8, P243 PERELMAN C, 1969, NEW RHETORIC TREATIS PROCHASKA J, 1994, HLTH PSYCHOL, V13 PROCHASKA J, 1992, PROGR BEHAV MODIFICA, V28 REED C, 2000, S ARG COMP REED C, 1998, P 36 ANN M ASS COMP, P1091 REITER E, 1999, LECT NOTES ARTIF INT, V1620, P389 SADALLA E, 1981, PSYCHOL TODAY, V15, P51 SEARLE J, 1969, SPEECH ACTS ESSAY PH STENT A, 2000, 740 U ROCH COMP SCI TEUFEL S, 1999, P EACL TOULMIN S, 1958, USES ARGUMENT Article", Abstract="Health promotion is a complex activity that requires both explanation and persuasion skills. This paper proposes a three-layered model of dialogue coding, based on a rhetorical argumentation model, and a behavioural model of change. The model was applied to the analysis of a corpus of 40 e-mail dialogue exchanges on healthy nutrition advice. Examples of analysis are given." Year=2003} @Article{grasso-eatl2000, Author="{Grasso, Floriana and Cawsey, A. and Jones, R.}", Title="{Dialectical argumentation to solve conflicts in advice giving: a case study in the promotion of healthy nutrition}", Journal="International Journal of Human-Computer Studies", Volume=53, Number=6, Pages="1077-1115", Note="Sp. Iss. SI", Abstract="Conflict situations do not only arise from misunderstandings, erroneous perceptions, partial, knowledge, false beliefs, etc., but also from differences in "opinions" and in the different agents' value systems. It is not always possible, and maybe not even desirable, to "solve" this kind of conflict, as the sources are subjective. The communicating agents can, however, use knowledge of the opponent's preferences, to try and convince the partner of a point of view which they wish to promote. To deal with these situations requires an argumentative capacity, able to handle not only "demonstrative" arguments but also "dialectic" ones, which may not necessarily be based on rationality and valid premises. This paper presents a formalization of a theory of informal argumentation, focused an techniques to change attitudes of the interlocutor, in the domain of health promotion. (C) 2000 Academic Press." Year=2000} @Article{green2010, Author="{Green, Nancy}", Title="{Representation of argumentation in text with Rhetorical Structure Theory}", Journal="Argumentation", Pages="to appear", Abstract="Various argumentation analysis tools permit the analyst to represent functional components of an argument (e.g., data, claim, warrant, backing), how arguments are composed of subarguments and defenses against potential counterarguments, and argumentation schemes. In order to facilitate a study of argument presentation in a biomedical corpus, we have developed a hybrid scheme that enables an analyst to encode argumentation analysis within the framework of Rhetorical Structure Theory (RST), which can be used to represent the discourse structure of a text. This paper describes the hybrid representation scheme and illustrates its use for investigation of contexts that license omission of elements of an argument. The analyses given in the paper involve reconstruction of enthymemes. Defeasible argumentation schemes serve as a constraint on reconstruction. In addition, the examples illustrate several other types of contextual constraints on reconstruction of enthymemes." Year=2010} @InProceedings{green-carberry92, Author="{Green, Nancy and Carberry, Sandra}", Title="{Conversational implicatures in indirect replies}", Booktitle="Proceedings of 30th Annual Meeting of the Association for Computational Linguistics (ACL'92)", Address="Newark, Delaware", Pages="64-71", Year=1992} @InProceedings{green-carberry94, Author="{Green, Nancy and Carberry, Sandra}", Title="{A hybrid reasoning model for indirect answers}", Booktitle="Proceedings of 32nd Annual Meeting of the Association for Computational Linguistics", Address="Las Cruces, New Mexico", Pages="58-65", Year=1994} @Article{green-carberry99, Author="{Green, Nancy and Carberry, Sandra}", Title="{Interpreting and generating indirect answers}", Journal="Computational Linguistics", Volume=25, Number=3, Pages="389-435", Abstract="This paper presents an implemented computational model for interpreting and generating indirect answers to yes-no questions in English. Interpretation and generation are treated, respectively, as recognition of and construction of a responder's discourse plan for a full answer. An indirect answer is the result of the responder providing only part of the planned response, but intending for his discourse plan to be recognized by the questioner. Discourse plan construction and recognition make use of shared knowledge of discourse strategies, represented in the model by discourse plan operators. In the operators, coherence relations are used to characterize types of information that may accompany each type of answer. Recognizing a mutually plausible coherence relation obtaining between the actual response and a possible direct answer plays an important role in recognizing the responder's discourse plan. During generation, stimulus conditions model a speaker's motivation for selecting a satellite. Also during generation, the speaker uses his own interpretation capability to determine what parts of the plan are inferable by the hearer and thus do not need to be explicitly given. The model provides wider coverage than previous computational models for generating and interpreting indirect answers and extends the plan-based theory of implicature in several ways." Year=1999} @Article{green-etal2004, Author="{Green, Nancy and Carenini, Giuseppe and Kerpedjiev, S. and Mattis, J. and Moore, Johanna D and Roth, S. F.}", Title="{AutoBrief: An experimental system for the automatic generation of briefings in integrated text and information graphics}", Journal="International Journal of Human-Computer Studies", Volume=61, Number=1, Pages="32-70", Abstract="This paper describes AutoBrief, an experimental intelligent multimedia presentation system that generates presentations in text and information graphics in the domain of transportation scheduling. Acting as an intelligent assistant, AutoBrief creates a presentation to communicate its analysis of alternative schedules. In addition, the multimedia presentation facilitates data exploration through its complex information visualizations and support for direct manipulation of presentation elements. AutoBrief's research contributions include (1) a design enabling a new human-computer interaction style in which intelligent multimedia presentation objects (textual or graphic) can be used by the audience in direct manipulation operations for data exploration, (2) an application-independent approach to multimedia generation based on the representation of communicative goals suitable for both generation of text and of complex information graphics, and (3) an application-independent approach to intelligent graphic design based upon communicative goals. This retrospective overview paper, aimed at a multidisciplinary audience from the fields of human-computer interaction and natural language generation, presents AutoBrief's design and design rationale. (C) 2003 Elsevier Ltd. All rights reserved." Year=2004} @Book{grimes, Author="{Grimes, Joseph E.}", Title="The Thread of Discourse", Publisher="Mouton", Address="The Hague", Year=1975} @PhDThesis{grommes2005, Author="Grommes, Patrick", Title="{Prinzipien kohärenter Kommunikation}", School="Humboldt Universität zu Berlin", Note="Citation of: thesis, 2003 IPrA presentation", Type="Ph.D. dissertation", Year=2005} @Article{grosz-sidner86, Author="{Grosz, Barbara J. and Sidner, Candace L.}", Title="{Attention, intentions, and the structure of discourse}", Journal="Computational Linguistics", Volume=12, Number=3, Pages="175-204", Abstract="Published before the first publication of RST, of course there is no mention, but GST is an important paper to have on hand, as it is often used as a point of comparison for RST, as well as a common subject for unification attempts with RST. In brief, the theory can use text with the same segmentation as RST, however relates larger pieces of text using only two discourse relations: Dominance and Satisfaction Precedence. Most notably, while there are fewer relations applying over larger spans, the end result is a hierarchical structure which is comparable to the higher levels of an RST analysis." Year=1986} @InCollection{grote-etal97, Author="{Grote, Brigitte and Hagen, Eli and Stein, Adelheit and Teich, Elke}", Title="{Speech production in human-machine dialogue: A Natural Language Generation perspective}", BookTitle="Dialogue Processing in Spoken Language Systems", Editor="Maier, Elisabeth and Mast, Marion and Luperfoy, Susan", Publisher="Springer", Address="Berlin", Pages="70-85", Abstract="Outlines a generation approach whereby text is generated and then sent to speech synthesis, filling a gap in current research focusing on recognition, or production of "canned" text. Intonation of generated speech is informed by the rhetorical relations being expressed. Further research is indicated to be neded for an investigation of prosodic realisation of textual relations." Year=1997} @Article{grote-etal97b, Author="{Grote, Brigitte and Lenke, Nils and Stede, Manfred}", Title="{Ma(r)king concessions in English and German}", Journal="Discourse Processes", Volume=24, Pages="87-117", Abstract="On the basis of an extensive corpus study, a new classification of Concession markers for English and German is proposed. Then, a generation model is presented for bilingual text that incorporates marker choice in its overall decision framework." Year=1997} @InProceedings{grote-stede98, Author="{Grote, Brigitte and Stede, Manfred}", Title="{Discourse marker choice in sentence planning}", Booktitle="Proceedings of 9th International Workshop on Natural Language Generation (IWNLG 9)", Address="Niagra-on-the-Lake, Canada", Pages="128-137", Year=1998} @InProceedings{groza-etal2007, Author="{Groza, Tudor and Handschuh, Siegfried and Moeller, Knud and Decker, Stefan}", Title="{SALT - Semantically Annotated LaTeX for scientific publications}", Booktitle="Proceedings of the 4th European Semantic Web Conference (ESWC 2007)", Address="Innsbruck, Austria", Pages="518-532", Year=2007} @InProceedings{groza-etal2006, Author="{Groza, Tudor and Kim, Hak Lae and Handschuh, Siegfried}", Title="{SALT: Enriching LATEX with semantic annotations}", Booktitle="Proceedings of the 5th International Semantic Web Conference (ISWC 2006)", Address="Athens, Ga." Year=2006} @InProceedings{groza-etal2008, Author="{Groza, Tudor and Möller, Knud and Handschuh, Siegfried and Trif, Diana and Decker, Stefan}", Title="{SALT: Weaving the claim web}", Booktitle="Proceedings of the 6th International Semantic Web Conference (ISWC 2007)", Address="Busan, Korea", Pages="197-210", Year=2007} @InProceedings{groza-etal-sigweb2007, Author="{Groza, Tudor and Schutz, Alexander and Handschuh, Siegfried}", Title="{SALT: A semantic approach for generating document representation}", Booktitle="Proceedings of 7th ACM Symposium on Document Engineering", Address="Winnipeg, MA", Pages="171-173", Year=2007} @Article{gruber-muntigl2005, Author="{Gruber, Helmut and Muntigl, Peter}", Title="{Generic and rhetorical structures of texts: Two sides of the same coin?}", Journal="Folia Linguistica", Volume=39, Number=1-2, Pages="75-113", Year=2005} @InProceedings{gundel-etal88, Author="{Gundel, Jeanette K. and Hedberg, Nancy and Zacharski, Ron}", Title="{On the generation and interpretation of demonstrative expressions}", Booktitle="Proceedings of 12th International Conference on Computational Linguistics (COLING'88)", Address="Budapest, Hungary", Pages="216-221", Year=1988} @Article{gurr97, Author="{Gurr, C. A.}", Title="{Knowledge engineering in the communication of information for safety critical systems}", Journal="Knowledge Engineering Review", Volume=12, Number=3, Pages="249-270", Abstract="The design and assessment of safety critical systems often involves broad and distributed teams of designers, suppliers and analysts who represent diverse areas of expertise and motivations. Accurate and effective communication between these groups is therefore an issue of primary importance. The formalisation of specifications and arguments of safety can be of significant benefit in ensuring the consistency of evidence in such cases, when it must be presented across many domains. However, a formal description of a safety critical system may be unconvincing unless it is presented in a form which is (or forms which are) accessible to the broad range of users and assessors of safety cases. This raises issues of human communication which include the tailoring of information to particular communicative tasks; the efficacy of differing media for communication and the cognitive impact that such differing media have. This paper draws together work in fields of knowledge engineering, knowledge based systems and human communication in an effort to address, from a sound theoretical basis, these and other communication issues raised by the use of formal descriptions in safety critical systems. Further, this paper argues that a primary role for knowledge based systems techniques in safety critical systems is in supporting the communication of information." Year=1997} @InProceedings{hachey-glover2004, Author="{Hachey, Ben and Grover, Claire}", Title="{A rhetorical status classifier for legal text summarisation}", Booktitle="Proceedings of Text Summarization Branches Out Workshop, 42nd Meeting of the Association for Computational Linguistics", Address="Barcelona, Spain", Year=2004} @PhDThesis{haddow2005, Author="Haddow, Barry", Title="{Acquiring a Disambiguation Model for Discourse Connectives}", School="University of Edinburgh", Type="M.Sc. Thesis", Year=2005} @Article{hagen99, Author="{Hagen, Eli}", Title="{An approach to mixed initiative spoken information retrieval dialogue}", Journal="User Modeling and User-Adapted Interaction", Volume=9, Number=1-2, Pages="167-213", Abstract="We present an approach to mixed initiative dialogue in acoustic user interfaces to databases. First, we discuss how we distinguish between initiative and control in mixed initiative information retrieval dialogue and how the notions of taking, keeping, and relinquishing initiative and control are reflected in our approach. Based on this discussion, we develop a dialogue planning algorithm. This algorithm distinguished between resources and routines and between the type and the content of an utterance; type and content are calculated separately by routines that reason on the resources - a dialogue model, a dialogue history, and an application description. Through this division we achieve a dialogue where the system adapts to the user's attempts at changing the direction of a dialogue. Finally, we argue that automatic segmentation of the dialogue and automatic tracking of initiative and control is inherent to our approach." Year=1999} @TechReport{hagen-etal94, Author="{Hagen, Eli and Stein, Adelheit and Bateman, John}", Title="{The Extension of a Rhetorical Component for the `Speak!' Dialogue System}", Institution="GMD/Institut für Integrierte Publikations- und Informationssysteme", Type="COPERNICUS Project 10393; Deliverable R3.2.2", Year=1994} @Article{hahn2002, Author="{Hahn, Udo}", Title="{The theory and practice of discourse parsing and summarization}", Journal="Computational Linguistics", Volume=28, Number=1, Pages="81-83", Year=2002} @Article{haller99, Author="{Haller, S.}", Title="{An introduction to interactive discourse processing from the perspective of plan recognition and text planning}", Journal="Artificial Intelligence Review", Volume=13, Number=4, Pages="259-311", Abstract="People engage in task-oriented dialogues to carry out or plan a task. Each participant in such an interaction must be capable of processing plans in two ways. First, each participant must be capable of understanding the plans that the other participant is using. Researchers have developed theories and models about how computational systems should go about recognizing the plans and goals of another participant, both at the subject-matter level and at the level of the communication. This area of research is called plan recognition. Secondly, each participant must be able to make their owns plans to communicate. This area of natural language research is called text planning. Interactive systems -- systems that understand natural language and that can produce natural language to engage in a task-related interaction -- must address the issue of how understanding plans (the process of plan recognition) relates to making plans for the interaction (the process of text planning). We provide an introduction to these two research areas in natural language processing. Those who need to be familiar with both areas -- to conduct research at their intersection -- will find this introduction useful for building systems that both understand what people are trying to do when they speak and that can actively participate in the interaction." Year=1999} @InCollection{hannay-hengeveld2009, Author="{Hannay, Mike and Hengeveld, Kees}", Title="{Functional Discourse Grammar: pragmatic aspects}", BookTitle="Grammar, Meaning and Pragmatics", Editor="Brisard, Frank and Östman, Jan-Ola and Verschueren, Jef", Publisher="John Benjamins", Address="Amsterdam", Pages="91-116", Note="Citation of Taboada and Mann 2006, part 1", Year=2009} @Article{hannay-kroon2005, Author="{Hannay, Mike and Kroon, Caroline}", Title="{Acts and the relationship between discourse and grammar}", Journal="Functions of Language", Volume=12, Number=1, Pages="87–124", Abstract="In modelling the discourse–grammar interface, a central question concerns the status of discourse act as the minimal unit of discourse organization and its relation to units of grammatical structure. This paper seeks to clarify the notion of act by defining it as a strategic rather than a conceptual unit, and by setting out a classification of strategic acts. Illustration is then offered for the position that discourse acts are to a very considerable extent realized in English by intonation units and punctuation units. This is done by considering how punctuational variation and cases of intonation/syntax mismatch can be explained in terms of the specific discourse contribution of the units concerned. Although the correlation between discourse acts and intonation/punctuation units remains problematic, in that there may not be a 1:1 correspondence, it is still attractive — at least for English — to see the linguistic correlate of acts in intonation and punctuation units rather than in syntactic structures. The paper finishes by considering the implications for the formalizing of relations between discourse, semantics and syntax in Functional Discourse Grammar." Year=2005} @InProceedings{hanneforth-etal2003, Author="{Hanneforth, Thomas and Heintze, Silvan and Stede, Manfred}", Title="{Rhetorical parsing with underspecification and forests}", Booktitle="Proceedings of HLT-NAACL 2003", Address="Edmonton, Canada", Year=2003} @InProceedings{haouam-marir2003, Author="{Haouam, Kamel and Marir, Fahri}", Title="{SEMIR: Semantic indexing and retrieving web document using Rhetorical Structure Theory}", Booktitle="Proceedings of the Fourth International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2003)", Address="Hong Kong", Pages="596-604", Year=2003} @Article{haouam-marir2006, Author="{Haouam, Kamel and Marir, Fahri}", Title="{A dynamic weight assignment approach for index terms}", Journal="Journal of Computer Science", Volume=2, Number=3, Pages="261-268", Abstract="The main objective of the weight assignment is to provide ranking feature to an IR system. The retrieval performance of an IR system mainly depends on two parameters: extraction of a good set of keywords from text documents, and the use of a good weight assignment approach. Most of currently available weight assignment approaches do not suggest any change to the weights of keywords after their initial assignment. It means that these approaches are static. In this paper, we propose a dynamic weight assignment approach for weight assignment. We use Rhetorical Structure Theory (RST) for indexing and retrieval purpose instead of keywords, and propose a dynamic weight assigned approach to the RST relationships. In our opinion, using this proposed approach can be helpful in improving the retrieval performance of an IR system. This approach can be used as part of any IR model after initial assignment of weights." Year=2006} @InProceedings{haouam-etal2003, Author="{Haouam, Kamel and Touir, A. and Marir, Fahri}", Title="{Towards a framework design of a retrieval document system based on Rhetorical Structure Theory and cue phrases}", Booktitle="Proceedings of the International Conference on New Trends in Intelligent Information Processing and Web Mining (IIS2003)", Address="Poland", Year=2003} @Article{harabagiu99, Author="{Harabagiu, Sanda}", Title="{From lexical cohesion to textual coherence: A data driven perspective}", Journal="International Journal of Pattern Recognition and Artificial Intelligence", Volume=13, Number=2, Pages="247-265", Abstract="This paper presents research that connects the cohesion structure of a text to the derivation of its coherence structure. Two different algorithms that derive the cohesion structure in the form of lexical paths from large thesauri are illustrated. Their results are correlated with (1) cue phrases of discourse usage and (2) coherence constraints empirically derived. A novel model of coherence structure is devised, based on the data provided by lexical paths from real world texts." Year=1999} @InProceedings{harabagiu-maiorano99, Author="{Harabagiu, Sanda and Maiorano, Steven}", Title="{Knowledge-lean coreference resolution and its relation to textual cohesion and coherence}", Booktitle="Proceedings of ACL Workshop on The Relation of Discourse/Dialogue Structure and Reference", Address="College Park, Maryland", Pages="29-38", Year=1999} @Article{hartley-paris97, Author="{Hartley, Anthony and Paris, Cécile}", Title="{Multilingual Document Production From Support for Translating to Support for Authoring}", Journal="Machine Translation", Volume=12, Number=1-2, Pages="109-129", Year=1997} @InProceedings{harvey-carberry98, Author="{Harvey, Terrency and Carberry, Sandra}", Title="{Integrating text plans for conciseness and coherence}", Booktitle="Proceedings of 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics", Address="Montréal, Canada", Pages="512-518", Year=1998} @InProceedings{hearst94, Author="{Hearst, Marti}", Title="{Multi-paragraph segmentation of expository text}", Booktitle="Proceedings of 32nd Annual Meeting of the Association for Computational Linguistics (ACL'94)", Address="Las Cruces, New Mexico", Pages="9-16", Year=1994} @InProceedings{henderson-desilva2006, Author="{Henderson, Peter and De Silva, Nishadi}", Title="{A narrative approach to collaborative writing: A business process model}", Booktitle="Proceedings of 8th International Conference on Enterprise Information Systems (ICEIS)", Address="Paphos, Cyprus." Year=2006} @InProceedings{hilbert-etal2006, Author="{Hilbert, Mirco and Lobin, Henning and Bärenfänger, Maja and Lüngen, Harald and Puskás, Csilla}", Title="{A text-technological approach to automatic discourse analysis of complex texts}", Booktitle="Proceedings of KONVENS 2006", Year=2006} @Article{hirst2002, Author="{Hirst, Graeme}", Title="{Patterns of text: In honour of Michael Hoey}", Journal="Computational Linguistics", Volume=28, Number=4, Pages="560-564", Year=2002} @Article{hobbs79, Author="{Hobbs, Jerry}", Title="{Coherence and coreference}", Journal="Cognitive Science", Volume=6, Pages="67-90", Abstract="Formal definitions for several relations are presented, based on the operations of an inference system. In illustrating the coherence of a discourse, coreference is demonstrated to be solved almost as a by-product, by means of "petty converational implicatures."", Year=1979} @TechReport{hobbs85, Author="{Hobbs, Jerry}", Title="{On the Coherence and Structure of Discourse}", Institution="CSLI", Type="Research Report 85-37", Abstract="Argues that discourse is structured, by means of coherence relations. Seeks to embed a theory of discourse relations in the larger context of a knowledge-based theory of discourse interpretation." Year=1985} @InProceedings{hobbs-nd, Author="{Hobbs, Jerry}", Title="An Approach to the Structure of Discourse", Note="Looking at the citations, this paper dates from 1995 or later, but an exact determination is not possible." Abstract="Argues for a seamless transition from syntax to discourse, grudgingly defining a minimal discourse unit as the minimal unit above which predicate relations are no longer the dominant interpretation of adjacency. Structures discourse with three broadly construed relations: causality, figure-ground, and similarity." Year=1993} @Article{hobbs-etal93, Author="{Hobbs, Jerry and Stickel, Mark E and Appelt, Douglas E and Martin, Paul}", Title="{Interpretation as abduction}", Journal="Artificial Intelligence", Volume=63, Pages="69-142", Abstract="The interpretation of a text is defined as the minimal explanation of why the text would be true. To interpret a text, one must prove the logical form of the text from what is mutually known, allowing for coercions, merging redundancies where possible, and making assumptions as necessary. Produces an elegant integration of syntax, semantics, and pragmatics, apparently spanning the range of linguistic phenomena from phonology to discourse structure." Year=1993} @Article{holler2007, Author="{Holler, A.}", Title="{Uniform or different? - On the syntactic status of non-restrictive relative clauses}", Journal="Deutsche Sprache", Volume=35, Number=3, Pages="250-270", Abstract="Relative clauses are usually differentiated according to their non-/restrictivity. Numerous theoretical studies look into questions such as how restrictive relative clauses can be distinguished from non-restrictive ones and to what extent the semantic-pragmatic differentiation between restrictive and non-restrictive relative clauses is based on structural differences. The present article tackles a problem that has generally been neglected in previous research. It investigates from a syntactic perspective whether the class of non-restrictive relative clauses behaves homogeneously. Based on empirical evidence it argues that (i) appositive relative clauses must be distinguished syntactically from continuative relative clauses, and that (ii) continuative w- and d-relative clauses show a uniform syntactic behaviour. In view of these facts, a syntactic analysis is proposed which treats an appositive relative clause and its nominal antecedent as one constituent, and a continuative relative clause as a structurally orphaned syntagma." Year=2007} @InProceedings{hovy88, Author="{Hovy, Eduard}", Title="{Planning coherent multisentential text}", Booktitle="Proceedings of 26th Annual Meeting of the Association for Computational Linguistics (ACL'88)", Address="Buffalo, New York", Pages="163-169", Year=1988} @InCollection{hovy90, Author="{Hovy, Eduard}", Title="{Unresolved issues in paragraph planning}", BookTitle="Current Research in Natural Language Generation", Editor="Dale, Robert and Mellish, Chris and Zock, Michael", Publisher="Academic Press", Address="London", Pages="17-45", Abstract="Discusses the (then) recent trend of planning paragraphs by dynamically assembling and manipulating the basic building blocks, using a paragraph structure tree. Presents issues with this approach, and possible solutions." Year=1990} @InProceedings{hovy-parsim90, Author="{Hovy, Eduard}", Title="{Parsimonious and profligate approaches to the question of discourse structure relations}", Booktitle="Proceedings of 5th International Workshop on Text Generation", Address="Pittsburgh, PA", Pages="59-65", Year=1990} @Article{hovy91, Author="{Hovy, Eduard}", Title="{Recent trends in computational research on monologic discourse structure}", Journal="Computational Intelligence", Volume=7, Pages="363-366", Abstract="Presents a state-of-the-union on the field. RST is mentioned only in the context of contributing to the growing collection of sets of relations." Year=1991} @Article{hovy92, Author="{Hovy, Eduard}", Title="{A New Level of Language Generation Technology - Capabilities and Possibilities}", Journal="IEEE Expert-Intelligent Systems & Their Applications", Volume=7, Number=2, Pages="12-17", Year=1992} @Article{hovy93, Author="{Hovy, Eduard}", Title="{Automated discourse generation using discourse structure relations}", Journal="Artificial Intelligence", Volume=63, Number=1-2, Pages="341-385", Abstract="Summarizes the previous five years of work on planning using relations. Outlines several facets of relations as required and used by planners: their nature, number and extension to tasks such as sentence planning and text formatting." Year=1993} @InCollection{hovy93b, Author="{Hovy, Eduard}", Title="{From interclausal relations to discourse structure- A long way behind, a long way ahead}", BookTitle="New Concepts in Natural Language Generation", Editor="Horacek, Helmut and Zock, Michael", Publisher="Pinter", Address="London", Pages="57-68", Abstract="Summary of ongoing research into the field of discourse structure as motivated by research into the generation of monologic discourse. Special emphasis is on the inquest into relations." Year=1993} @InProceedings{hovy95, Author="{Hovy, Eduard}", Title="{The multifunctionality of discourse markers}", Booktitle="Proceedings of Workshop on Discourse Markers", Address="Egmond-aan-Zee", Year=1995} @InProceedings{hovy-arens91, Author="{Hovy, Eduard and Arens, Yigal}", Title="{Automatic generation of formatted text}", Booktitle="Proceedings of 9th AAAI Conference", Address="Anaheim, California", Year=1991} @InCollection{hovy-etal92, Author="{Hovy, Eduard and Lavid, Julia and Maier, Elisabeth and Mittal, Vibhu and Paris, Cécile}", Title="{Employing knowledge resources in a new text planning architecture}", BookTitle="Aspects of Automated Natural Language Generation", Editor="Dale, Robert and Hovy, Eduard and Rösner, Dietmar and Stock, Oliviero", Publisher="Springer", Address="Berlin", Pages="57-72", Abstract="RST as a part of a larger text planning system. As communicative goals are realised and pushed/popped from stack, supportive relations may be triggered. Databases are queried to see if any information meeting the needs of the relation in focus is available for introduction into the text. In this model, RST seems to be subordinated under other processes, as communicative goals seem to construct the spine of the text; the RST relations branch downwards from these communicative goals, and there is no indication of cross-goal interaction. A hierarchy of relations (original M&T 88 with some additions by Hovy) is also presented. At the macro level, there are three major classes: INTERPERSONAL, IDEATIONAL, TEXTUAL." Year=1992} @InProceedings{hovy-lin97, Author="{Hovy, Eduard and Lin, Chin Yew}", Title="{Automated text summarization in Summarist}", Booktitle="Proceedings of ACL/EACL Workshop on Intelligent Scalable Text Summarization", Address="Madrid", Pages="18-24", Year=1997} @TechReport{hovy-maier, Author="{Hovy, Eduard and Maier, Elisabeth}", Title="{Parsimonious or Profligate: How Many and Which Discourse Structure Relations?}", Institution="Information Sciences Institute", Type="Technical Report ISI/RR-93-373." Year=1992} @InProceedings{hovy-maier95, Author="{Hovy, Eduard and Maier, Elisabeth}", Title="Parsimonious or Profligate: How Many and Which Discourse Structure Relations?" Abstract="Categorises ten years of research into relations from the two-relation G&S to the open-ended RST, coming up with a final list of over 400 relations, fused down into 70 "increasingly semantic" relations. Also includes a full list of sources." Year=1995} @Article{huffman-laird95, Author="{Huffman, S. B. and Laird, J. E.}", Title="{Flexibly instructable agents}", Journal="Journal of Artificial Intelligence Research", Volume=3, Pages="271-324", Abstract="This paper presents an approach to learning from situated, interactive tutorial instruction within an ongoing agent. Tutorial instruction is a flexible (and thus powerful) paradigm for teaching tasks because it allows an instructor to communicate whatever types of knowledge an agent might need in whatever situations might arise. To support this flexibility, however, the agent must be able to learn multiple kinds of knowledge from a broad range of instructional interactions. Our approach, called situated explanation, achieves such learning through a combination of analytic and inductive techniques. It combines a form of explanation-based learning that is situated for each instruction with a full suite of contextually guided responses to incomplete explanations. The approach is implemented in an agent called INSTRUCTO-SOAR that learns hierarchies of new tasks and other domain knowledge from interactive natural language instructions. INSTRUCTO-SOAR meets three key requirements of flexible instructability that distinguish it from previous systems: (1) it can take known or unknown commands at any instruction point; (2) it can handle instructions that apply to either its current situation or to a hypothetical situation specified in language (as in, for instance, conditional instructions); and (3) it can learn, from instructions, each class of knowledge it uses to perform tasks." Year=1995} @InCollection{hulstijn-etal2005, Author="{Hulstijn, J. and Dignum, F. and Dastani, M.}", Title="{Coherence constraints for agent interaction}", BookTitle="Agent Communication", Series="Lecture Notes in Computer Science", Volume=3396, Pages="134-152", Abstract="This paper describes the use of coherence constraints as a means to regulate agent interaction. Coherence constraints describe relationships between the content of utterances, and the context. They can be used for example to express that an answer must refer back in a meaningful way to the question that it answers. We also discuss several possible ways in which the enforcement of coherence constraints can be implemented in a multiagent system. Finally we describe a possible implementation in the 3APL platform, which shows the feasibility of this form of interaction regulation." Year=2005} @Article{hunter2001, Author="{Hunter, A.}", Title="{Hybrid argumentation systems for structured news reports}", Journal="Knowledge Engineering Review", Volume=16, Number=4, Pages="295-329", Abstract="Numerous argumentation systems have been proposed in the literature. Yet there often appears to be a shortfall between proposed systems and possible applications. In other words, there seems to be a need for further development of proposals for argumentation systems before they can be used widely in decision-support or knowledge management. I believe that this shortfall can be bridged by taking a hybrid approach. Whilst formal foundations are vital, systems that incorporate some I of the practical ideas found in some of the informal approaches may make the,resulting hybrid systems more useful. In informal approaches, there is often an emphasis on using graphical notation with symbols that relate more closely to the real-world concepts to be modelled. There may also be the incorporation of an argument ontology oriented to the user domain. Furthermore, in informal approaches there can be greater consideration of how users interact with the models, such as allowing users to edit arguments and to weight influences on graphs representing arguments. In this paper, I discuss some of the features of argumentation, review some key formal argumentation systems, identify some of the strengths and weaknesses of these formal proposals and finally consider some ways to develop formal proposals to give hybrid argumentation systems. To focus my discussions, I will consider some applications, in particular an application in analysing structured news reports." Year=2001} @PhDThesis{huong2004, Author="Huong, Le Thanh", Title="{Automatic Discourse Structure Generation Using Rhetorical Structure Theory}", School="Middlesex University", Type="Ph.D. dissertation", Year=2004} @Article{huong2007, Author="{Huong, Le Thanh}", Title="{An approach in automatically generating discourse structure of text}", Journal="Journal of Computer Science and Cybernetics", Volume=23, Number=3, Pages="212-230", Year=2007} @InProceedings{le-abeysinghe2003, Author="{Huong, Le Thanh and Abeysinghe, Geetha}", Title="{A study to improve the efficiency of a discourse parsing system}", Booktitle="Proceedings of 4th International Conference on Intelligent Text Processing and Computational Linguistics", Publisher="Springer", Address="Berlin", Pages="101-114", Year=2003} @InProceedings{huong-etal2003, Author="{Huong, Le Thanh and Abeysinghe, Geetha and Huyck, Christian}", Title="{Using cohesive devices to recognize rhetorical relations in text}", Booktitle="Proceedings of 4th Computational Linguistics UK Research Colloquium (CLUK 4)", Address="University of Edinburgh, UK", Year=2003} @Article{hwang2005, Author="{Hwang, S. J. J.}", Title="{Complex sentences in grammar and discourse: Essays in honor of Sandra A. Thompson}", Journal="Word-Journal of the International Linguistic Association", Volume=56, Number=2, Pages="270-277", Note="Cited References: BYBEE J, 2002, COMPLEX SENTENCES GR HAIMAN J, 1988, CLAUSE COMBINING GRA LONGACRE RE, 1985, LANGUAGE TYPOLOGY SY, V2, P235 MANN WC, 1988, TEXT, V8, P243 MATTHIESSEN C, 1988, CLAUSE COMBINING GRA, P275 THOMPSON SA, 2002, STUD LANG, V26, P125 WIERZBICKA A, 1993, STUD LANG, V17, P437 Book Review", Year=2005} @InProceedings{ide-cristea2000, Author="{Ide, Nancy and Cristea, Dan}", Title="{A hierarchical account of referential accessibility}", Booktitle="Proceedings of the 38th Meeting of the Association for Computational Linguistics", Address="Hong Kong", Pages="416 - 424", Year=2000} @InProceedings{inder-oberlander95, Author="{Inder, Robert and Oberlander, Jon}", Title="{Using discourse to aid Hypertext navigation}", Booktitle="Proceedings of 6th International Conference on Human-Computer Interaction (HCI)", Address="Tokyo, Japan", Pages="195-200", Year=1995} @InProceedings{iruskieta-etal2009, Author="{Iruskieta Quintian, Mikel and Díaz de Ilarraza Sánchez, Arantxa and Lersundi Ayestaran, Mikel}", Title="{Correlaciones en euskera entre las relaciones retóricas y los marcadores del discurso}", BookTitle="Conferencia de la Asociación Española de Lingüística Aplicada", Address="Ciudad Real (Spain)", Note="Citation of Taboada (2006, Jof Prags), RST site", Year=2009} @InProceedings{jayez-rossari98, Author="{Jayez, Jacques and Rossari, Corinne}", Title="{Discourse relations versus discourse marker relations}", Booktitle="Proceedings of ACL Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="72-78", Year=1998} @InCollection{ji-etal2006, Author="{Ji, P.}", Title="{Multi-document summarization based on unsupervised clustering}", BookTitle="Information Retrieval Technology, Proceedings", Series="Lecture Notes in Computer Science", Volume=4182, Pages="560-566", Abstract="In this paper, we propose a method for multi-document summarization based on unsupervised clustering. First, the main topics are determined by a MDL-based clustering strategy capable of inferring optimal cluster numbers. Then, the problem of multi-document summarization is formalized on the clusters using an entropy-based object function." Year=2006} @Article{johnsen2001, Author="{Johnsen, L.}", Title="{Document (re)presentation: Object-orientation, visual language, and XML}", Journal="Technical Communication", Volume=48, Number=1, Pages="59-65", Abstract="Argues that document analysis and design can integrate ideas from modern text theory into object-oriented thinking Demonstrates how object-orientation and visual language may be used to map text structures onto perceptual object configurations." Year=2001} @InCollection{jordan92, Author="{Jordan, Michael P.}", Title="{An integrated three-pronged analysis of a fund-raising letter}", BookTitle="Discourse Description: Diverse Linguistic Analyses of a Fund-Raising Text", Editor="Mann, William C. and Thompson, Sandra A." Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="171-226", Abstract="Presents an integrated analysis of the ZPG letter using clause relations (Which is in itself an integration of numerous other approaches, including RST), lexical connections, and problem-solution structures. Includes a very detailed diagram of the analysis." Year=1992} @Book{kamalski2007, Author="{Kamalski, Judith}", Title="Coherence Marking, Comprehension and Persuasion: On the Processing and Representation of Discourse", Publisher="LOT", Address="Utrecht", Year=2007} @Article{kaplan-grabe2002, Author="{Kaplan, R. B. and Grabe, W.}", Title="{A modem history of written discourse analysis}", Journal="Journal of Second Language Writing", Volume=11, Number=3, Pages="191-223", Abstract="The term discourse analysis has been used interchangeably in two separate contexts spoken discourse (i.e., multiple-source dialogic) and written discourse (i.e., single-source monologic). Such a distinction, however, oversimplifies the situation; while there are obvious overlaps between the two, to some extent each has evolved in its own direction. Written discourse analysis, the subject of our discussion, is obviously closely connected with work in literacy, but it implicates a great heterogeneity of topics and approaches, including at least some from psycholinguistics and sociolinguistics. Discourse analysis, in the sense in which we are using it, emerged in the early 1970s. A modem history of written discourse analysis is perhaps best covered within a 40-50-year time span. In the course of that time, a number of new and emerging disciplines and research fields have contributed to systematic analyses of the linguistic features and patterns occurring in written texts. At the same time, other continuing disciplines have provided contributions that have been important and are ongoing. It should be fairly evident that any attempt to cover such a broad spectrum of views and disciplines would not be appropriate in a single article. We therefore intend to limit the scope of this paper to analyses of written discourse that explore the actual structuring of the text via some consistent framework. Our goal is to highlight and describe historically the various efforts to find the structures and linguistic patterns in texts that contribute to how they are understood, interpreted, and used. It seems to us that, in order to comprehend what has happened in the context of L2 writing research, it is necessary to understand the extensive work that has been done in discourse analysis. (C) 2002 Elsevier Science Inc. All rights reserved." Year=2002} @Article{karamanis2007, Author="{Karamanis, Nikiforos}", Title="{Supplementing entity coherence with local rhetorical relations for information ordering}", Journal="Journal of Logic, Language and Information", Volume=16, Pages="445-464", Note="Citation of Taboada, J of Pragmatics 2006", Year=2007} @Article{karoly98, Author="{Károly, Krisztina}", Title="{Written text analysis: A multidisciplinary field of study}", Journal="Sprachtheorie und germanistische Linguistik", Volume=8, Number=1, Pages="71-108", Abstract="A critical review of the six approaches to English written text analysis that have the greatest influence on recent work in the field situates them on a cline from primarily language-based to primarily psychological & cognitive orientations: (1) the cohesion analysis of M. A. K. Halliday & R. Hasan (1976), (2) Hasan's (1984) cohesive harmony, (3) J. Swales's (1990) genre analysis, (4) R. B. Kaplan's (1987) contrastive rhetoric, (5) the relational proposition analysis (1986) & rhetorical structure theory (1988) of W. C. Mann & S. A. Thompson, & (6) W. Kintsch's & T. Van Dijk's (1978) proposition analysis. Although Kaplan's work ranges across the cline, it is judged excessively intuitive & lacking in methodological rigor & consistency; other approaches are argued to be too limited in disciplinary perspective, & all need revision for greater precision. It is concluded that the complexity of text demands a multidisciplinary perspective. 6 Tables, 10 Figures, 39 References. J. Hitchcock", Year=1998} @InCollection{katz-allbritton2002, Author="{Katz, S. and Allbritton, D.}", Title="{Going beyond the problem given: How human tutors use post-practice discussions to support transfer}", BookTitle="Intelligent Tutoring Systems", Series="Lecture Notes in Computer Science", Volume=2363, Pages="641-650", Abstract="Recent studies reveal that human tutoring sessions do not always end when the student has solved a problem. Instead, tutors and students frequently use a post-practice discussion to bring new topics to the table or to continue problem-solving discussions. One of the main roles of post-practice dialogues is to support transfer-that is, the student's ability to apply concepts and adapt familiar solution strategies to unfamiliar problems. Several developers of intelligent tutoring systems have implemented post-practice modules, with similar aims. However, in contrast to the integrated instructional planning that human tutors apparently perform, automated planning of reflective activities is typically done independently of instructional planning during problem solving. We present a framework for describing reflective plans that are distributed between problem solving and debrief and evidence that reflective discussions support transfer in elementary mechanics." Year=2002} @Article{katzav-reed2008, Author="{Katzav, J. and Reed, C.}", Title="{Modelling argument recognition and reconstruction}", Journal="Journal of Pragmatics", Volume=40, Number=1, Pages="155-172", Abstract="A growing body of recent work in informal logic investigates the process of argumentation. Among other things, this work focuses on the ways in which individuals attempt to understand written or verbalised arguments in light of the fact that these are often presented in forms that are incomplete and unmarked. One of its aims is to develop general procedures for natural language argument recognition and reconstruction. Our aim here is to draw on this growing body of knowledge in informal logic in order to take preliminary steps towards developing an architecture for computer systems that are able to recognise and reconstruct natural language arguments. This architecture aims to structure research of an applied and computational nature that strives to implement linguistic systems of various sorts, and to analyse problems in a way that both yields manageable and relatively independent components and also highlights how implementations can interact with existing resources from natural language processing. (c) 2007 Elsevier B.V. All rights reserved." Year=2008} @Article{keenan-etal84, Author="{Keenan, Janice M. and Baillet, Susan D. and Brown, Polly}", Title="{The effects of causal cohesion on comprehension and memory}", Journal="Journal of Verbal Learning and Verbal Behaviour", Volume=23, Number=2, Pages="115-126", Abstract="Two experiments are reported in which sentence-by-sentence reading times were collected on two-sentence paragraphs, where the first sentence specified a cause for the event in the second sentence. Each paragraph had four versions. All versions had the same second sentence and were referentially coherent; they differed, however, in the causal relatedness of the two sentences. Despite referential coherence, reading times for second sentences were shown to steadily increase as causal relatedness decreased. Recognition and recall memory for the causes was poorest for the most and least related causes and best for causes of intermediate levels of relatedness." Year=1984} @PhDThesis{kehler95, Author="Kehler, Andrew", Title="{Interpreting Cohesive Forms in the Context of Discourse Inference}", School="Harvard", Type="Ph.D. dissertation", Abstract="Provides an algorithm for solving cohesive phenomena such as VP-ellipsis, gapping, event reference, tense, and pronominal reference. Argues that these must be informed by discourse level processing, specifically an awareness of relations. The Thesis outlines the theory of relations which informs this algorithm", Year=1995} @Book{kehler2002, Author="{Kehler, Andrew}", Title="Coherence, Reference, and the Theory of Grammar", Publisher="CSLI", Address="Stanford, CA", Year=2002} @Article{khoo-na2006, Author="{Khoo, C. S. G. and Na, J. C.}", Title="{Semantic relations in information science}", Journal="Annual Review of Information Science and Technology", Volume=40, Pages="157-228", Year=2006} @InCollection{khoo-etal, Author="{Khoo, C. S. G. and Ou, S. Y. and Goh, D. H. L.}", Title="{A hierarchical framework for multi-document summarization of dissertation abstracts}", BookTitle="Digital Libraries: People, Knowledge, and Technology, Proceedings", Series="Lecture Notes in Computer Science", Volume=2555, Pages="99-110", Abstract="This paper reports initial work on developing methods for automatic generation of multi-document summaries of dissertation abstracts in a digital library. The focus is on automatically generating a summary of a set of dissertation abstracts retrieved in response to user query, and presenting the summary using a visualization method. A hierarchical variable-based framework for multi-document summarization of dissertation abstracts in sociology and psychology is presented. The framework makes use of macro-level and micro-level discourse structure of dissertation abstracts as well as cross-document structure. The micro-level structure of problem statements found in a sample of 50 dissertation abstracts was analyzed, and the common features found are described in the paper. A demonstration prototype with a tree-view interface for presenting multi-document abstracts has been implemented." Year=2002} @Article{kibble2007, Author="{Kibble, Rodger}", Title="{Generating coherence relations via internal argumentation}", Journal="Journal of Logic, Language and Information", Volume=16, Number=4, Pages="387-402", Note="Citation of Taboada and Mann, paper 1", Year=2007} @InProceedings{kibble-power2001, Author="{Kibble, Rodger and Power, Richard}", Title="{Using Centering Theory to plan coherent texts}", Booktitle="Proceedings of the 12th Amsterdam Colloquium", Address="Amsterdam, The Netherlands", Pages="187-192", Year=1999} @Article{kibble-power2004, Author="{Kibble, Rodger and Power, Richard}", Title="{Optimizing referential coherence in text generation}", Journal="Computational Linguistics", Volume=30, Number=4, Pages="401-416", Abstract="This article describes an implemented system which uses centering theory for planning of coherent texts and choice of referring expressions. We argue that text and sentence planning need to be driven in part by the goal of maintaining referential continuity and thereby facilitating pronoun resolution: Obtaining a favorable ordering of clauses, and of arguments within clauses, is likely to increase opportunities for nonambiguous pronoun use. Centering theory provides the basis for such an integrated approach. Generating coherent texts according to centering theory is treated as a constraint satisfaction problem. The well-known Rule 2 of centering theory is reformulated in terms of a set of constraints—cohesion, salience, cheapness, and continuity—and we show sample outputs obtained under a particular weighting of these constraints. This framework facilitates detailed research into evaluation metrics and will therefore provide a productive research tool in addition to the immediate practical benefit of improving the fluency and readability of generated texts. The technique is generally applicable to natural language generation systems, which perform hierarchical text structuring based on a theory of coherence relations with certain additional assumptions." Year=2004} @Article{kim-etal2007, Author="{Kim, Sanghee and Bracewell, Rob H. and Wallace, Ken M.}", Title="{Answering engineers' questions using semantic annotations}", Journal="Artificial Intelligence for Engineering Design Analysis and Manufacturing", Volume=21, Number=2, Pages="155-171", Note="Citation of Discourse Studies article (Looking back...)", Abstract="Question-answering (QA) systems have proven to be helpful, especially to those who feel uncomfortable entering keywords, sometimes extended with search symbols such as +, *, and so forth. In developing such systems, the main focus has been on the enhanced retrieval performance of searches, and recent trends in QA systems center on the extraction of exact answers. However, when their usability was evaluated, some users indicated that they found it difficult to accept the answers because of the absence of supporting context and rationale. Current approaches to address this problem include providing answers with linking paragraphs or with summarizing extensions. Both methods are believed to be sufficient to answer questions seeking the names of objects or quantities that have only a single answer, However, neither method addresses the situation when an answer requires the comparison and integration of information appearing in multiple documents or in several places in a single document. This paper argues that coherent answer generation is crucial for such questions, and that the key to this coherence is to analyze texts to a level beyond sentence annotations. To demonstrate this idea, a prototype has been developed based on rhetorical structure theory, and a preliminary evaluation has been carried out. The evaluation indicates that users prefer to see the extended answers that can be generated using such semantic annotations, provided that additional context and rationale information are made available." Year=2007} @Article{kittredge2002, Author="{Kittredge, R.}", Title="{Paraphrasing for condensation in journal abstracting}", Journal="Journal of Biomedical Informatics", Volume=35, Number=4, Pages="265-277", Abstract="When authors of empirical science articles write abstracts, they employ a wide variety of distinct linguistic operations which interact to condense and rephrase a subset of sentences from the source text. An on-going comparison of biological and biomedical journal articles with their author-written abstracts is providing a basis for a more linguistically detailed model of abstract derivation using syntactic representations of selected source sentences. The description makes use of rich dictionary information to formulate paraphrasing rules of differing degrees of generality, including some which are sublanguage-specific, and others which appear valid in several languages when formulated using "lexical functions" to express important semantic relationships between lexical items. Some paraphrase operations may use both lexical functions and rhetorical relations between sentences to reformulate larger chunks of text in a concise abstract sentence. The descriptive framework is computable and utilizes existing linguistic resources. (C) 2003 Elsevier Science (USA). All rights reserved." Year=2002} @Article{kittredge-etal91, Author="{Kittredge, Richard and Korelsky, Tanya and Rambow, Owen}", Title="{On the need for domain communication language}", Journal="Computational Intelligence", Volume=7, Pages="305-314", Year=1991} @Article{kleiber-vassiliadou2009, Author="{Kleiber, Georges and Vassiliadou, Hélène}", Title="{Sur la relation d'Élaboration: des approches intuitives aux approches formelles}", Journal="Journal of French Language Studies", Volume=19, Number=2, Pages="183-205", Note="Citation of Taboada and Mann 2006, part 1", Year=2009} @Article{kneser-ploetzner2001, Author="{Kneser, C. and Ploetzner, R.}", Title="{Collaboration on the basis of complementary domain knowledge: observed dialogue structures and their relation to learning success}", Journal="Learning and Instruction", Volume=11, Number=1, Pages="53-83", Abstract="We present an analysis of dialogues produced in an experimental study on collaborative learning. In the study, tenth graders were first taught either qualitative or quantitative knowledge of classical mechanics. Afterwards, dyads of students who had been taught different knowledge collaboratively worked on problems which were beyond the competence of each student, Qualitatively instructed students gained significantly more from the information provided by their quantitatively instructed partners than the other way round. Analyses of the dialogues produced by the students revealed that successfully learning dyads were characterised by coherent dialogue structures and that students who learned most during the collaboration frequently assumed the role of a reflector. (C) 2000 Elsevier Science Ltd. All rights reserved." Year=2001} @PhDThesis{knott96, Author="Knott, Alistair", Title="{A Data-Driven Methodology for Motivating a Set of Coherence Relations}", School="University of Edinburgh", Type="Ph.D. dissertation", Abstract="In search of a definitive list and classification of discourse relations. Begins with a study of markers, the taxonomy of which leads nicely into a feature-based taxonomy of relations. Ends with new set of relation definitions, and has a very useful appendix listing markers." Year=1996} @InProceedings{knott98, Author="{Knott, Alistair}", Title="{Similarity and contrast relations and inductive rules}", Booktitle="Proceedings of ACL Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="54-57", Year=1998} @InCollection{knott2001, Author="{Knott, Alistair}", Title="{Semantic and pragmatic relations and their intended effects}", BookTitle="Text Representation: Linguistic and Psycholinguistic Aspects", Editor="Sanders, Ted and Schilperoord, Joost and Spooren, Wilbert", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="127-151", Year=2001} @Article{knott2007, Author="{Knott, A.}", Title="{Coherence in natural language: Data stuctures and applications}", Journal="Computational Linguistics", Volume=33, Number=4, Pages="591-595", Year=2007} @Article{knott-dale94, Author="{Knott, Alistair and Dale, Robert}", Title="{Using linguistic phenomena to motivate a set of coherence relations}", Journal="Discourse Processes", Volume=18, Number=1, Pages="35-62", Abstract="Presentation of a bottom-up methodology for the identification and formal definition of coherence relations based on solid usage data, as opposed to nebulously defined notions of intentions and semantics." Year=1994} @InCollection{knott-dale96, Author="{Knott, Alistair and Dale, Robert}", Title="{Choosing a set of coherence relations for text generation: A data-driven approach}", BookTitle="Trends in Natural Language Generation: an Artificial Intelligence Perspective", Editor="Adorni, Giovanni and Zock, Michael", Publisher="Springer", Address="Berlin", Pages="47-67", Abstract="Seems to be a short version of Knott's thesis. Outlines the process from building the list of markers through to the taxonomy of relations. Mentions the one loophole in the methodology: relations with no overt cue. In RST, this is usually the elaboration relation. The solution to this problem is left to future research." Year=1996} @Article{knott-mellish96, Author="{Knott, Alistair and Mellish, Chris}", Title="{A feature-based account of the relations signalled by sentence and clause connectives}", Journal="Language and Speech", Volume=39, Number=2-3, Pages="143-183", Abstract="Presents a three stage process investigating the relationship between discourse cues and relations. First, a large corpus of connectives is assembled. Then, the corpus is organized into a taxonomy of synonyms and hyponyms. Finally, a theoretical interpretation is imposed on the taxonomy. The final step is the focus of the paper, in which relations can be defined in terms of a number of orthogonal multi-valued features, and connectives as signallers of feature values." Year=1996} @InCollection{knott-etal2001, Author="{Knott, Alistair and Oberlander, Jon and O'Donnell, Michael and Mellish, Chris}", Title="{Beyond elaboration: The interaction of relations and focus in coherent text}", BookTitle="Text Representation: Linguistic and Psycholinguistic Aspects", Editor="Sanders, Ted and Schilperoord, Joost and Spooren, Wilbert", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="181-196", Abstract="Follows up a question leftover from Knott's thesis. Proposes to drop Elaboration from the set of relations. Interclausal and -sentential relational trees take care of local coherence, and global coherence is managed by global focus." Year=2001} @Article{knott-sanders, Author="{Knott, Alistair and Sanders, Ted}", Title="{The classification of coherence relations and their linguistic markers: An exploration of two languages}", Journal="Journal of Pragmatics", Volume=30, Pages="135-175", Abstract="Combines Knott's English corpus work with Sanders psycholinguistic experiments on speakers of Dutch in order to determine sets of coherence relations. These processes both lead to classifications of markers and relations for each language which are then compared and some interesting congruencies are noted. Hard copy currently on file is incomplete. (Right margin missing)", Year=1998} @Article{knott-sanders-oberlander2001, Author="{Knott, A. and Sanders, T. and Oberlander, J.}", Title="{Levels of representation in discourse relations}", Journal="Cognitive Linguistics", Volume=12, Number=3, Pages="197-209", Year=2001} @Article{kong98, Author="{Kong, Kenneth C. C.}", Title="{Are simple business request letters really simple? A comparison of Chinese and English business request letters}", Journal="Text", Volume=18, Number=1, Pages="103-141", Abstract="Presents a comparison study of Chinese and English business letters using RST and and Swales' move structure analysis. It is found that the two languages use quite different rhetorical styles, owing to the general different discourse patters of the two languages, and to the different social implications of making requests in each language group. The Chinese letters are dominated by face-deference while the English ones reflect face-solidarity, and these different face moves are reflected in the rhetorical structure. There is also a comparison of the two theoretical approaches used to determine their relative strenghts and weaknesses." Year=1998} @InProceedings{korelsky-kittredge93, Author="{Korelsky, Tanya and Kittredge, Richard}", Title="{Towards stratification of RST}", Booktitle="Proceedings of ACL Workshop on Intentionality and Structure in Discourse Relations", Address="Ohio State University", Pages="52-55", Year=1993} @InProceedings{kosseim-lapalme94, Author="{Kosseim, Leila and Lapalme, Guy}", Title="{Content and rhetorical status selection in instructional texts}", Booktitle="Proceedings of 7th International Workshop on Natural Language Generation", Address="Kennebunkport, Maine", Pages="53-60", Year=1994} @Article{kosseim-lapalme, Author="{Kosseim, Leila and Lapalme, Guy}", Title="{Choosing rhetorical structures to plan instructional texts}", Journal="Computational Intelligence", Volume=16, Number=3, Pages="408-445", Abstract="Presents a system for the automatic generation of French instructional text, identifying 9 semantic carriers common to French instructional text, and the 7 RST relations used to represent them." Year=2000} @InProceedings{krasavina2004, Author="{Krasavina, Olga}", Title="{Use of the third-person pronouns and rhetorical structure: A corpus-oriented study}", Booktitle="Proceedings of 5th Discourse Anaphora and Anaphora Resolution Colloquium (DAARC 2004)", Address="Lisbon, Portugal", Year=2004} @InCollection{krifka-dobes-novak93, Author="{Krifka-Dobes, Zuzana and Novak, Hans-Joachim}", Title="{From constituent planning to text planning}", BookTitle="New Concepts in Natural Language Generation: Planning, Realization, and Systems", Editor="Horacek, Helmut and Zock, Michael", Publisher="Pinter", Address="London", Pages="87-113", Abstract="In the framework of the LILOG (Linguistic & Logic Methods for the Automatic Understanding of German) project, a text-planning structure based on rhetorical structure theory (RST) is introduced, which allows for input structures above the clause level to be combined by rhetorical relations, thus increasing the flexibility & realizability of computer text generation. LILOG's analysis component & knowledge representation/inference engine are described, addressing its use of a head-driven phrase structure grammar-based syntactic/semantic parser to generate an extended discourse representation structure (EDRS) of input, followed by an evaluation of the proposed RST-based planning schemas in analyzing input EDRSs & planning, revising, & generating appropriate responses to user queries. 2 Figures, 22 References. Adapted from the source document", Year=1993} @Article{kuperberg-etal2006, Author="{Kuperberg, Gina R. and Lakshmanan, Balaji M. and Caplan, David N. and Holcomb, Phillip J}", Title="{Making sense of discourse: An fMRI study of causal inferencing across sentences}", Journal="NeuroImage", Volume=33, Number=1, Pages="343-361", Abstract="To build up coherence between sentences (comprehend discourse), we must draw inferences, i.e. activate and integrate information that is not actually stated. We used event-related fMRI to determine the localization and extent of brain activity mediating causal inferencing across short, three-sentence scenarios. Participants read and made causal coherence judgments to sentences that were highly causally related, intermediately related or unrelated to their preceding two-sentence contexts. The highly related and intermediately related scenarios were matched in terms of semantic similarities between their individual component words. A pre-rating study established that causal inferences were generated to the intermediately related but not to the highly related or unrelated scenarios. In the scanner, sentences that were intermediately related (relative to highly related or unrelated) to their preceding contexts were associated with longer judgment reaction times and sustained increases in hemodynamic activity within left lateral temporal/inferior parietal/prefrontal cortices, the right inferior prefrontal gyrus and bilateral superior medial prefrontal cortices. In contrast, sentences that were unrelated (relative to highly related) to their preceding contexts were associated with only transient increases in activity (at, but not after, the peak of the hemodynamic response) within the right lateral temporal cortex and the right inferior prefrontal gyrus. These data suggest that, to make sense of discourse, we activate a large bilateral cortical network in response to what is not explicitly stated. We suggest that this network reflects the activation, retrieval and integration of information from long-term semantic memory into incoming discourse structure during causal inferencing." Year=2006} @InProceedings{kurohashi-nagao94, Author="{Kurohashi, Sadao and Nagao, Makoto}", Title="{Automatic detection of discourse structure by checking surface information in sentences}", Booktitle="Proceedings of 15th International Conference on Computational Linguistics (COLING'94)", Address="Kyoto, Japan", Pages="1123-1127", Year=1994} @Article{kuronen-etal2005, Author="{Kuronen, M. L. and Tienari, J. and Vaara, E.}", Title="{The merger storm recognizes no borders: An analysis of media rhetoric on a business manoeuvre}", Journal="Organization", Volume=12, Number=2, Pages="247-273", Abstract="Despite the central role of the media in contemporary society, studies examining the rhetorical practices of journalists are rare in organization and management research. We know little of the textual micro strategies and techniques through which journalists convey specific messages to their readers. Partially to fill the gap, this paper outlines a methodological framework that combines three perspectives of text analysis and interpretation: critical discourse analysis, systemic functional grammar and rhetorical structure theory. Using this framework, we engage in a close reading of a single media text (a press article) on a recent case of industrial restructuring in the financial services. In our empirical analysis, we focus on key arguments put forward by the journalists' rhetorical constructions. We maintain that these arguments-which are not frame-breaking but rather tend to confirm existing presuppositions held by the audience-are an essential part of the legitimization and naturalization of specific management ideas and ideologies." Year=2005} @Book{lagerwerf98, Author="{Lagerwerf, Luuk}", Title="Causal Connectives Have Presuppositions: Effects on Coherence and Discourse Structure", Publisher="Holland Academic Graphics", Address="The Hague", Year=1998} @Article{lagerwerf-etal2008, Author="{Lagerwerf, Luuk and Cornelis, L. and de Geus, J. and Jansen, P.}", Title="{Advance organizers in advisory reports - Selective reading, recall, and perception}", Journal="Written Communication", Volume=25, Number=1, Pages="53-75", Abstract="According to research in educational psychology, advance organizers lead to better learning and recall of information. In this research, the authors explored advance organizers from a business perspective, where larger documents are read under time pressure. Graphic and verbal advance organizers were manipulated into six versions of an advisory report, read by 159 experienced professional readers in a between-subjects design. Their reading time was limited to encourage selective reading. The results show that graphic advance organizers facilitate selective reading, but they do not enhance recall. Verbal advance organizers introducing a problem enhance recall, and graphic advance organizers moderate the effects on both selective reading and recall." Year=2008} @Article{lagerwerf2006, Author="{Lagerwerf, Luuk and Spooren, Wilbert and Degand, Liesbeth}", Title="{Surface cues of content and tenor in texts - Introduction}", Journal="Discourse Processes", Volume=41, Number=2, Pages="111-116", Year=2006} @InProceedings{lascarides-asher91, Author="{Lascarides, Alex and Asher, Nicholas}", Title="{Discourse relations and defeasible knowledge}", Booktitle="Proceedings of 29th Annual Meeting of the Association for Computational Linguistics (ACL'91)", Address="Berkeley, California", Pages="55-62", Year=1991} @Article{lascarides-asher93, Author="{Lascarides, Alex and Asher, Nicholas}", Title="{Temporal interpretation, discourse relations and commonsense entailment}", Journal="Linguistics and Philosophy", Volume=16, Number=5, Pages="437-493", Abstract="Formal methodology for determining the relations between text, and the relation between the events described therein. Interestingly, temporal judgements are made without having to resort to the examination of tense or aspect." Year=1993} @InProceedings{lascarides-etal92, Author="{Lascarides, Alex and Asher, Nicholas and Oberlander, Jon}", Title="{Inferring discourse relations in context}", Booktitle="Proceedings of 30th Annual Meeting of the Association for Computational Linguistics", Address="Newark, Delaware", Pages="1-8", Year=1992} @Article{lascarides-oberlander93, Author="{Lascarides, Alex and Oberlander, Jon}", Title="{Temporal coherence and defeasible knowledge}", Journal="Theoretical Linguistics", Volume=19, Pages="1-37", Abstract="Presents a logical account for the coherence of discourse, with a focus on the relation between clause ordering in text, and causal ordering in the real world. Questions are raised about the relation between clause order in discourse and causal order in the world, and about the coherence of certain discourses. It transpires that a constrained set of reasoning patterns underlies the retrieval of certain temporal structures. They also discuss defeasible reasoning in language generation, and some consequences for the semantics-pragmatics interface." Year=1993} @Article{lavid-taboada-jtwc, Author="{Lavid, Julia and Taboada, Maite}", Title="{Stylistic differences in document design across languages in Europe: A cross-linguistic characterization}", Journal="Journal of Technical Writing and Communications", Volume=34, Number=1-2, Pages="43-65", Year=2004} @Article{draoulec-pery-woodley2005, Author="{Le Draoulec, A. and Pery-Woodley, M. P.}", Title="{Temporal management and discourse relations}", Journal="Langue Francaise", Number=148, Pages="45-+", Note="Cited References: ASHER N, 1993, REFERENCE ABSTRACT O CHAROLLES M, ADVERBIAUX DETACHES CHAROLLES M, IN PRESS J FRENCH LA CHAROLLES M, 1997, CAHIER RECHERCHE LIN, V6 CHAROLLES M, 2003, TRAVAUX LINGUIST, V47, P11 ENKVIST NE, 1985, TEXT CONNEXITY TEXT, P320 FAUCONNIER G, 1984, ESPACES MENTAUX GROSZ B, 1986, COMPUTATIONAL LINGUI, V12, P175 GUIMIER C, 1996, ADVERBES FRANCAIS CO HALLIDAY MAK, 1967, J LINGUIST, V3, P199 HALLIDAY MAK, 1967, J LINGUIST, V3, P37 HALLIDAY MAK, 1968, J LINGUIST, V4, P179 HALLIDAY MAK, 1976, COHESION ENGLISH HALLIDAY MAK, 1980, 7 LACUS FOR HALLIDAY MAK, 1985, INTRO FUNCTIONAL GRA HASSELGARD H, 2004, P 14 EUR INT SYST FU HOBBS JR, 1985, COHERENCE STRUCTURE HODAC LM, IN PRESS THESIS U TO LEDRAOULEC A, IN PRESS ENCADREMENT LEDRAOULEC A, 2001, CORPUS LINGUISTICS 2, P159 LEDRAOULEC A, 2003, DETERMINATION INFORM, P267 MANN WC, 1988, TEXT, P243 MOLINIER C, 2000, GRAMMAIRE ADVERBES M PREVOST S, 2003, TRAVAUX LINGUISTIQUE, V47 SCHREPFER G, UNPUB INCIDENCE FORM TERRAN E, 2002, THESIS U PARIS 3 THOMPSON SA, 1985, TEXT, V5, P55 Article", Abstract="In this study of temporal framing, we examine the interaction between "indexing" via temporal discourse frames and another mode of discourse organisation: connection via discourse relations. This interaction is shown to be problematic in the case of the Narration relation, as Narration implies a temporal progression which conflicts with the static nature of temporal frames, often making it difficult to determine the scope of a frame introducing expression. We suggest that two separate dimensions ought to be taken into account in the framing hypothesis: the ideational dimension (whereby the frame introducer plays an indexing role in the strict sense) and the textual dimension (whereby the introducer is characterised by its ability to delimit a text segment). We show that in contact with the Narration relation, temporal framing loses its ideational dimension, but maintains its role in discourse organisation (textual dimension). We also suggest that this dual nature of framing should be studied through the interaction between temporal frames and other discourse relations such as Commentary or Background. Our approach to these questions relies mostly on corpus analysis, but also uses made-up examples." Year=2005} @Article{le2003, Author="{Le, E.}", Title="{Information sources as a persuasive strategy in editorials - Le Monde and the New York times}", Journal="Written Communication", Volume=20, Number=4, Pages="478-510", Abstract="The media, which includes editorials, have been shown to play an important role in the definition of priorities in public agenda. In the domain of international matters, the public relies heavily on the media, and editorials play an even greater role. This article examines how explicit mentions of external sources of information function in the argumentative structure of editorials to achieve a persuasive effect. A corpus of 40 editorials dealing with Russia (taken from Le Monde and The New York Times between August 1999 and March 2000) has been studied using a cognitive-based linguistic model of discourse analysis. It is shown how under the guise of bringing some objectivity to the editorials' argumentation, external sources of information facilitate and enhance their subjectivity." Year=2003} @InProceedings{le-abeysinghe2003, Author="{Le, Huong T and Abeysinghe, Geetha}", Title="{A study to improve the efficiency of a discourse parsing system}", Booktitle="Proceedings of 4th International Conference on Intelligent Text Processing and Computational Linguistics", Publisher="Springer", Address="Berlin", Pages="101-114", Year=2003} @TechReport{lindley-etal2001, Author="{Lindley, Craig and Davis, Jim and Nack, Frank and Rutledge, Lloyd}", Title="{The Application of Rhetorical Structure Theory to Interactive News Program Generation from Digital Archives}", Institution="Centrum voor Wiskunde en Informatica", Number="INS-R0101", Type="Technical Report", Abstract="Begins with a discussion of the applicability of RST to multimedia presentations, and provides an RST analysis of a BBC news broadcast. There is also discussion of how aranging the same video segments into a different RST structure would alter the editorial thrust of the news broadcast. The paper concludes with a discussion of the possibilities for RST as a generated of coherent presentations (aranging pieces of smaller material into a larger presentation) and the limits thereof." Year=2001} @InProceedings{litman-passoneau95, Author="{Litman, Diane J. and Passonneau, Rebecca}", Title="{Combining multiple knowledge sources for discourse segmentation}", Booktitle="Proceedings of 33rd Annual Meeting of the Association for Computational Linguistics (ACL'95)", Address="Cambridge, Massachusetts", Pages="108-115", Year=1995} @Book{longacre, Author="{Longacre, Robert E.}", Title="An Anatomy of Speech Notions", Publisher="The Peter de Ridder Press", Address="Lisse", Year=1976} @Book{longacre83, Author="{Longacre, Robert E.}", Title="The Grammar of Discourse", Publisher="Plenum", Address="New York", Year=1983} @InCollection{lorenz99, Author="{Lorenz, Gunter}", Title="{Learning to cohere: Causal links in native vs. non-native argumentative writing}", BookTitle="Coherence in Spoken and Written Discourse: How to Create It and How to Describe It", Editor="Bublitz, Wolfram and Lenk, Uta and Ventola, Eija", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="56-75", Abstract="Presents a corpus study of markers of Cause and Effect relations in the writing of German ESL learners, with an aim towards measuring the connection bewtween connective usage and the subjective acceptability of the texts." Year=1999} @Article{louwerse2001, Author="{Louwerse, Max M.}", Title="{An analytic and cognitive parametrization of coherence relations}", Journal="Cognitive Linguistics", Volume=12, Number=3, Pages="291-315", Abstract="An analytic and cognitive parameterization of coherence relations is proposed that contains the categories TYPE (CAUSAL, TEMPORAL, ADDITIVE), POLARITY (POSITIVE, NEGATIVE), and DIRECTION (FORWARD, BI-DIRECTIONAL, and BACKWARD). Evidence for the parameterization comes from the first of a series of studies. An eye-tracking study and a self-paced reading-time experiment provide tentative cognitive evidence for the proposed types of coherence relations." Year=2001} @InProceedings{lungen-etal2006, Author="{Lüngen, Harald and Bärenfänger, Maja and Hilbert, Mirco and Lobin, Henning and Puskás, Csilla}", Title="{Text parsing of a complex genre}", Booktitle="Proceedings ELPUB2006 Conference on Electronic Publishing", Address="Bankso, Bulgaria", Pages="247-256", Year=2006} @InCollection{madjid-etal2003, Author="{Madjid, I. and Stephane, C. and Daniel, M.}", Title="{The effect of individual differences on searching the Web}", BookTitle="Asist 2003: Proceedings of the 66th Asist Annual Meeting, Vol 40, 2003", Series="Proceedings of the Asist Annual Meeting", Volume=40, Pages="240-246", Abstract="This paper reports results from a project which sought to investigate the influence of two types of expertise - the knowledge of the search domain and the experience of the Web search engines - on the use of a Web search engine, called Exalead, by a panel of students. Forty six students (twenty four undergraduate students in psychology and twenty two undergraduates in other disciplines) were asked to give correct answers to eight questions about definitions of psychology concepts, without any time constraint. Results show that participants with good knowledge in the domain on the one hand and participants with high experience of the Web on the other had the best performances. Participants with low experience of the Web showed less effectiveness than the other participants. Future research is proposed to know the best aids to users of information retrieval systems." Year=2003} @PhDThesis{mahlow2006, Author="Mahlow, Morris", Title="{Entwicklung und Vergleich von zwei Verfahren zur Auswertung von deutschen Freitextkommentaren}", School="Universität Potsdam", Type="Diplomarbeit", Year=2006} @InProceedings{maier91, Author="{Maier, Elisabeth}", Title="{Zwei Texttheorien in neuem Licht - RST und GSP fuers Abstracting}", BookTitle="Workshop Textzusammenfassen at the yearly GAL conference", Address="Mainz, Germany", Year=1991} @InCollection{maier96b, Author="{Maier, Elisabeth}", Title="{Textual relations as part of multiple links between text segments}", BookTitle="Trends in Natural Language Generation: An Artificial Intelligence Perspective", Editor="Adorni, Giovanni and Zock, Michael", Publisher="Springer", Address="Berlin", Pages="68-87", Year=1996} @InProceedings{maier-hovy91, Author="{Maier, Elisabeth and Hovy, Eduard}", Title="{A metafunctionally motivated taxonomy for discourse structure relations}", Booktitle="Proceedings of 3rd European Workshop on Language Generation", Address="Innsbruck, Austria", Year=1991} @InCollection{maier-hovy93, Author="{Maier, Elisabeth and Hovy, Eduard}", Title="{Organising discourse structure relations using metafunctions}", BookTitle="New Concepts in Natural Language Generation", Editor="Horacek, Helmut and Zock, Michael", Publisher="Pinter", Address="London", Pages="69-86", Abstract="Presents a hierarchical taxonomy of relations broadly based on the three-way Hallidayan distinction of ideational, interpersonal, and textual." Year=1993} @InProceedings{maier-sitter92, Author="{Maier, Elisabeth and Sitter, Stefan}", Title="{An extension of rhetorical structure theory for the treatment of retrieval dialogues}", Booktitle="Proceedings of the Fourteenth Annual Conference of the Cognitive Science Society", Address="Bloomington, IN", Pages="968–973", Year=1992} @Article{mancini-etal2006, Author="{Mancini, Clara and Scott, Donia and Shum, Simon Buckingham}", Title="{Visualizing discourse coherence in non-linear documents}", Journal="Traitement Automatique des Langues", Volume=47, Number=2, Pages="137-168", Abstract="To produce coherent linear documents, natural language generation systems have traditionally exploited the structuring role of textual discourse markers such as relational and referential phrases. These coherence markers of the traditional notion of text, however, do not work in non-linear documents: a new set of graphical devices is needed together with formation rules to govern their usage, supported by sound theoretical frameworks. If in linear documents graphical devices such as layout and formatting complement textual devices in the expression of discourse coherence, in non-linear documents they play a more important role. In this paper, we present our theoretical and empirical work in progress, which explores new possibilities for expressing coherence in the generation of hypertext documents." Year=2006} @Article{mancini-shum2006, Author="{Mancini, Clara and Shum, Simon J. Buckingham}", Title="{Modelling discourse in contested domains: A semiotic and cognitive framework}", Journal="International Journal of Human-Computer Studies", Volume=64, Number=11, Pages="1154-1171", Abstract="This paper examines the representational requirements for interactive, collaborative systems intended to support sensemaking and argumentation over contested issues. We argue that a perspective supported by semiotic and cognitively oriented discourse analyses offers both theoretical insights and motivates representational requirements for the semantics of tools for contesting meaning. We introduce our semiotic approach, highlighting its implications for discourse representation, before describing a research system (ClaiMaker) designed to support the construction of scholarly argumentation by allowing analysts to publish and contest 'claims' about scientific contributions. We show how ClaiMaker's representational scheme is grounded in specific assumptions concerning the nature of explicit modelling, and the evolution of meaning within a discourse community. These characteristics allow the system to represent scholarly discourse as a dynamic process, in the form of continuously evolving structures. A cognitively oriented discourse analysis then shows how the use of a small set of cognitive relational primitives in the underlying ontology opens possibilities for offering users advanced forms of computational service for analysing collectively constructed argumentation networks. (c) 2006 Elsevier Ltd. All rights reserved." Year=2006} @TechReport{mann83a, Author="{Mann, William C.}", Title="{An Overview of the Nigel Text Generation Grammar}", Institution="ISI/RR-83-113. Information Sciences Institute, University of Southern California", Year=1983} @TechReport{mann83b, Author="{Mann, William C.}", Title="{An Overview of the Penman Text Generation Grammar}", Institution="ISI/RR-83-114. Information Sciences Institute, University of Southern California", Year=1983} @InProceedings{mann-intro-spa, Author="{Mann, William C.}", Title="Introducción a la Teoría de la Estructura Retórica (Rhetorical Structure Theory: RST)", Abstract="An updated introduction to RST, in Spanish. Essentially a condensed version of M&T 88." Year=1999} @InProceedings{mann-poq, Author="{Mann, William C.}", Title="Pretty Open Questions (POQ's) about RST", Abstract="Presents a summary of yet-to-be-resolved issues surrounding RST." Year=2000} @InProceedings{mann-website, Author="{Mann, William C.}", Title="RST Web Site", Year=2003} @InCollection{mann-intentions2003, Author="{Mann, William C.}", Title="{Models of intentions in language}", BookTitle="Perspectives on Dialogue in the New Millennium", Editor="Kühnlein, Peter and Rieser, Hannes and Zeevat, Henk", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="165-178", Year=2003} @Article{mann-matthiessen91, Author="{Mann, William C. and Matthiessen, Christian M.I.M.}", Title="{Functions of language in two frameworks}", Journal="Word", Volume=42, Number=3, Pages="231-249", Abstract="Presents a comparison of RST and Systemic Linguistics. A tight correspondence is demonstrated. Primary focus is on the correlation between RST's relations and the categories of function found in systemic linguistics." Year=1991} @InCollection{mann-etal92, Author="{Mann, William C. and Matthiessen, Christian M.I.M. and Thompson, Sandra A.}", Title="{Rhetorical Structure Theory and text analysis}", BookTitle="Discourse Description: Diverse Linguistic Analyses of a Fund-Raising Text", Editor="Mann, William C. and Thompson, Sandra A." Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="39-78", Abstract="Presents a thorough introduction to RST, in the context of an analysis of the infamous ZPG letter." Year=1992} @InProceedings{mann-website-sfu, Author="{Mann, William C. and Taboada, Maite}", Title="RST Web Site", Year=2007} @TechReport{mann-thompson83, Author="{Mann, William C. and Thompson, Sandra A.}", Title="{Relational Propositions in Discourse}", Institution="Information Sciences Institute", Number="ISI/RR-83-115", Type="Technical Report", Abstract="Pre-RST, this paper presents an account of "implicit propositions" in text and a means of distinguishing them. There are also examples from actual text, including a detailed examination of the Syncom text, which is later assigned an RST structure in 1988. The relations are shown to hold for every clause, but the hierarchical structure is not yet present." Year=1983} @TechReport{mann-thompson-report86, Author="{Mann, William C. and Thompson, Sandra A.}", Title="{Rhetorical Structure Theory: Description and Construction of Text Sructures}", Institution="Information Sciences Institute", Number="ISI/RS-86-174", Type="Technical Report", Year=1986} @TechReport{mann-thompson87, Author="{Mann, William C. and Thompson, Sandra A.}", Title="{Rhetorical Structure Theory: A Theory of Text Organization}", Institution="Information Sciences Institute", Number="ISI/RS-87-190", Month="June 1987", Year=1987} @Article{mann-thompson88, Author="{Mann, William C. and Thompson, Sandra A.}", Title="{Rhetorical Structure Theory: Toward a functional theory of text organization}", Journal="Text", Volume=8, Number=3, Pages="243-281", Abstract="The Gold-Standard of RST definitions. Includes our favourite quote "By eschewing obfuscatory verbosity of locutional rendering, the circumscriptional appelations are excised."", Year=1988} @InCollection{mann-thompson92, Author="{Mann, William C. and Thompson, Sandra A.}", Title="{Relational Discourse Structure: A comparison of approaches to structuring text by 'contrast'}", BookTitle="Language in Context: Essays for Robert E. Longacre", Editor="Hwang, Shin Ja J. and Merrifield, William R." Publisher="Summer Institute of Linguistics and the University of Texas at Arlington", Address="Dallas", Pages="19-45", Abstract="Presents a comparison of a number of approaches (including RST) to the notion of contrast, frustrated expectation, and surprise. Another: A comparative study of the work of 10 researchers & research teams in the field of relations among discourse units in written texts focuses on a set of relations broadly described as contrastive. Three theoretical orientations are distinguished, based on selection from three groups of assumptions, which are modeled as concentric circles yielding, in outward order, semantic, speech-act, & social-act orientations. Emphasis is placed on a description of three relations of rhetorical structure theory: antithesis, concession, & neutral contrast. Whereas antithesis & concession involve a nucleus & satellite, neutral contrast is multinuclear, consisting of two nuclear spans, neither of which is central. It is shown that concession, considered elsewhere to be contrastive, does not express contrast. 33 References. J. Hitchcock", Year=1992} @PhDThesis{mantynen2003, Author="Mantynen, Anne Kaarina", Title="{Talking about Language: The Rhetoric of Language Columns}", School="University of Helsinki", Note="Available from UMI, Ann Arbor, MI. Order No. C813682." Type="PhD dissertation", Abstract="The study focuses on the genre of language columns and the ways Finnish language professionals talk about language. From the perspective of the analysis, one needs to take into consideration the context and discourse practices of a genre when defining the genre of a text. The material of the study consists of 204 language columns in Finnish newspapers. Methodologically the study is based on genre analysis and the techniques of the New Rhetoric. It also applies Rhetorical Structure Theory and metaphor theory. The study demonstrates that in the analysis of genre, the socio-cultural and historical contexts are fundamental. The following aspects pertaining to the development of modern Standard Finnish are apparently vital: national values, language planning and major dictionary projects. Furthermore, the rhetorical analysis shows that the authorities used in the columns are classical and established authors and works, whereas contemporary research is marginally represented. In the analysis of schematic structures one finds two prototypical schemes used in the columns: (1) the problem-solution scheme, and (2) the general-example scheme. These schemes are already suggested by the way a text begins, and they also have different functions. The problem-solution scheme begins with an interrogative or a discourse representation allowing for the discussion of normative issues. The general example scheme begins either with a relational process or a statement, and the typical topics discussed are individual words or particular phenomena. The analysis of metaphors shows that language is conceptualised through metaphors, which can be divided into two semes (minimal units of signification) related either to nature or to culture. Nature metaphors are used to describe language change in which people can, however, have a guiding role. Culture metaphors, then, are related to the societal and contractual aspects of language. The characteristic type of argument of the language columns is the empirical argument, realised through the use of examples and verbs of perception and emotion. These can be used both for reasoning and for evaluation. Negative evaluations especially are expressed through impressions of strangeness." Year=2003} @InProceedings{marcu96, Author="{Marcu, Daniel}", Title="{Building up rhetorical structure trees}", Booktitle="Proceedings of 13th National Conference on Artificial Intelligence", Address="Portland, Oregon", Pages="1069-1074", Year=1996} @InProceedings{marcu96b, Author="{Marcu, Daniel}", Title="{Distinguishing between coherent and incoherent texts}", Booktitle="Proceedings of Student Conference on Computational Linguistics in Montréal", Address="Montréal, Canada", Pages="136-143", Year=1996} @InProceedings{marcu97, Author="{Marcu, Daniel}", Title="{From local to global coherence: A bottom-up approach to text planning}", Booktitle="Proceedings of 14th National Conference on Artificial Intelligence", Address="Providence, Rhode Island", Pages="629-635", Year=1997} @InProceedings{marcu97b, Author="{Marcu, Daniel}", Title="{The rhetorical parsing of natural language texts}", Booktitle="Proceedings of 35th Annual Meeting of the Association for Computational Linguistics, (ACL'97/EACL'97)", Address="Madrid, Spain", Pages="96-103", Year=1997} @InProceedings{marcu97c, Author="{Marcu, Daniel}", Title="{From discourse structures to text summaries}", Booktitle="Proceedings of ACL Workshop on Intelligent Scalable Text Summarisation", Address="Madrid, Spain", Pages="82-88", Year=1997} @PhDThesis{marcu97d, Author="Marcu, Daniel", Title="{The Rhetorical Parsing, Summarization, and Generation of Natural Language Texts}", School="University of Toronto", Note="The Citeseer page has the wrong Bibtex entry, but following the pdf link does get to the thesis. If in doubt, visit Marcu's homepage." Type="Ph.D. dissertation", Abstract="Large-Scale exploration of Marcu's work to-date. Includes comparisons to other theories (G&S, Polanyi, Hovy) not included elsewhere. Also has appendices containing lists of relations and markers used for the corpus analysis." Year=1997} @InProceedings{marcu98, Author="{Marcu, Daniel}", Title="{To build text summaries of higher quality, nuclearity is not sufficient}", Booktitle="Proceedings of AAAI-98 Spring Symposium on Intelligent Text Summarization", Address="Stanford, California", Pages="1-8", Year=1998} @InProceedings{marcu98b, Author="{Marcu, Daniel}", Title="{A surface-based approach to identifying discourse markers and elementary textual units in unrestricted texts}", Booktitle="Proceedings of COLING-ACL Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="1-7", Year=1998} @InProceedings{marcu98c, Author="{Marcu, Daniel}", Title="{Improving summarization through rhetorical parsing tuning}", Booktitle="Proceedings of ACL 6th Workshop on Very Large Corpora", Address="Montréal, Canada", Pages="206-215", Year=1998} @InProceedings{marcu99, Author="{Marcu, Daniel}", Title="{A decision-based approach to rhetorical parsing}", Booktitle="Proceedings of 37th Annual Meeting of the Association for Computational Linguistics (ACL'99)", Address="College Park, Maryland", Pages="365-372", Year=1999} @InCollection{marcu99b, Author="{Marcu, Daniel}", Title="{Discourse trees are good indicators of importance in texts}", BookTitle="Advances in Automatic Text Summarization", Editor="Mani, Inderjeet and Maybury, Mark", Publisher="The MIT Press", Pages="123-136", Abstract="Recaps all summarization work to date. No original ideas." Year=1999} @InProceedings{marcu99c, Author="{Marcu, Daniel}", Title="Instructions for Manually Annotating the Discourse Structures of Texts", Pages="50", Note="MANUAL OUT OF DATE! Carlson Marcu 2001 is now the standard." Abstract="This is the protocol for the Tree Corpus building experiment. Within, there are instructions on how to use the RST tree building software, definitions of all the relations, including helpful hints on how to identify relations, and instructions for relation selection when more than one is possible. This last is formulated similar to a control structure in a piece of software code, using if and elseif statements." Year=1999} @InProceedings{marcu99d, Author="{Marcu, Daniel}", Title="{A formal and computational synthesis of Grosz and Sidner's and Mann and Thompson's theories}", Booktitle="Proceedings of Workshop on Levels of Representation in Discourse", Address="Edinburgh, Scotland", Pages="101-108", Year=1999} @Article{marcu2000, Author="{Marcu, Daniel}", Title="{The rhetorical parsing of unrestricted texts: A surface based approach}", Journal="Computational Linguistics", Volume=26, Number=3, Pages="395-448", Abstract="This is a published summary of all of Marcu's work at U of T, leading up to his PhD Thesis. The rhetorical parser is discussed in detail once again, starting from the corpus study of discourse markers (which is actually discussed in more detail here than in previous papers), all the way through to weighted trees and applications for text summarisation. The shift-reduce algorithm as presented here is also more involved, looking similar to the Japanese version of (Marcu Carlson Watanabe 2000). It emerges that paragraph boundaries are counted as discourse markers in the corpus. Also making a first appearance is the notion of matching similar words as a means of determining the relatedness of spans. This paper also touches on several other discourse approach." Year=2000} @InProceedings{marcu2000b, Author="{Marcu, Daniel}", Title="{Extending a formal and computational model of Rhetorical Structure Theory with intentional structures a la Grosz and Sidner}", Booktitle="The 18th International Conference on Computational Linguistics (COLING'00)", Address="Saarbrücken, Germany", Pages="523-529", Year=2000} @Book{marcu-book, Author="{Marcu, Daniel}", Title="The Theory and Practice of Discourse Parsing and Summarization", Publisher="MIT Press", Address="Cambridge, Mass", Year=2000} @InProceedings{marcu-etal2000, Author="{Marcu, Daniel and Carlson, Lynn and Watanabe, Maki}", Title="{The automatic translation of discourse structures}", Booktitle="1st Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL'00)", Address="Seattle, Washington", Pages="9-17", Year=2000} @InProceedings{marcu-etal2000b, Author="{Marcu, Daniel and Carlson, Lynn and Watanabe, Maki}", Title="{An empirical study in multilingual Natural Language Generation: What should a text planner do?}", Booktitle="First International Conference on Natural Language Generation (INLG'2000)", Address="Mitzpe Ramon, Israel", Pages="17-23", Year=2000} @InProceedings{marcu-echihabi2002, Author="{Marcu, Daniel and Echihabi, Abdessamad}", Title="{An unsupervised approach to recognising discourse relations}", Booktitle="Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL'02)", Address="Philadelphia, Pennsylvania", Pages="368-375", Year=2002} @InProceedings{marcu-etal99, Author="{Marcu, Daniel and Romera, Magdalena and Amorrortu, Estibaliz}", Title="{Experiments in constructing a corpus of discourse trees}", Booktitle="Proceedings of ACL Workshop on Standards and Tools for Discourse Tagging", Address="College Park, Maryland", Pages="48-57", Year=1999} @InProceedings{marcu-etal99b, Author="{Marcu, Daniel and Romera, Magdalena and Amorrortu, Estibaliz}", Title="{Experiments in constructing a corpus of discourse trees: Problems, annotation choices, issues}", Booktitle="Workshop on Levels of Representation in Discourse", Address="Edinburgh, UK", Pages="71-78", Year=1999} @InProceedings{marir-haouam2002, Author="{Marir, Fahri and Haouam, Kamel}", Title="{RSTIndex: Indexing and retrieving web document using computational and linguistic techniques}", Booktitle="Proceedings of the Third International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2002)", Address="UK", Pages="135-140", Year=2002} @InProceedings{marir-haouam-itre2004, Author="{Marir, Fahri and Haouam, Kamel}", Title="{Rhetorical Structure Theory for content-based indexing and retrieval of Web documents}", Booktitle="Proceedings of the 2nd International Conference Information Technology: Research and Education (ITRE 2004)", Address="UK", Year=2004} @Book{martin92, Author="{Martin, James R.}", Title="English Text: System and Structure", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Year=1992} @InProceedings{maslennikov-chua2007, Author="{Maslennikov, Mstislav and Chua, Tat-seng}", Title="{A multi-resolution framework for information extraction from free text}", Booktitle="Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics", Address="Prague, Czech Republic", Pages="592-599", Year=2007} @Article{matthiessen-ob2005, Author="{Matthiessen, Christian M.I.M.}", Title="{Remembering Bill Mann}", Journal="Computational Linguistics", Volume=31, Number=2, Pages="161-172", Year=2005} @Book{matthiessen-bateman91, Author="{Matthiessen, Christian M.I.M. and Bateman, John}", Title="Text Generation and Systemic-Functional Linguistics: Experiences from English and Japanese", Publisher="Pinter", Address="London and New York", Year=1991} @InCollection{matthiessen-thompson88, Author="{Matthiessen, Christian M.I.M. and Thompson, Sandra A.}", Title="{The structure of discourse and "subordination"}", BookTitle="Clause Combining in Discourse and Grammar", Editor="Haiman, John and Thompson, Sandra A." Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="275-329", Abstract="Presents an account of defining the term "subordinate clause" using discourse function as opposed to the traditional syntactic account. In the process, an early sketch of RST and some of the relations is presented." Year=1988} @InProceedings{matthiessen-etal98, Author="{Matthiessen, Christian M.I.M. and Zeng, Licheng and Cross, Marilyn and Kobayashi, Ichiro and Teruya, Kazuhiro and Wu, Canzhong}", Title="{The Multex generator and its environment: Application and development}", Booktitle="Proceedings of ACL Workshop on Natural Language Generation", Address="Montréal, Canada", Pages="228-237", Year=1998} @TechReport{mcIlmoil2001, Author="{McIlmoil, Tara}", Title="{Using RST Lite to Teach Organisational Structure and Coherence}", Type="Essay", Abstract="Presents RST-Lite, which is essentially RST using a condensed set of relations, then makes pedagogical suggestions for the use of RST-Lite for teaching coherence and writing style." Year=2001} @Article{mckeown-etal95, Author="{McKeown, Kathleen and Robin, Jacques and Kukich, Karen}", Title="{Generating concise natural language summaries}", Journal="Information Processing and Management", Volume=31, Number=5, Pages="703-733", Note="The link is to a Gzipped ps file. This is not included with the PDF files because my computer is unable to cope with this file." Abstract="Presents a new methodology for the generation of summaries by enfolding information on several facts into one concise sentence. Unlike other models, how information is added depends on the wording of the text so far. Not even a citation of RST." Year=1995} @Book{mckeown85, Author="{McKeown, Kathleen R.}", Title="Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text", Publisher="Cambridge University Press", Address="Cambridge", Year=1985} @Article{mctear2002, Author="{McTear, M. F.}", Title="{Spoken dialogue technology: Enabling the conversational user interface}", Journal="Acm Computing Surveys", Volume=34, Number=1, Pages="90-169", Abstract="Spoken dialogue systems allow users to interact with computer-based applications such as databases and expert systems by using natural spoken language. The origins of spoken dialogue systems can be traced back to Artificial Intelligence research in the 1950s concerned with developing conversational interfaces. However, it is only within the last decade or so, with major advances in speech technology, that large-scale working systems have been developed and, in some cases, introduced into commercial environments. As a result many major telecommunications and software companies have become aware of the potential for spoken dialogue technology to provide solutions in newly developing areas such as computer-telephony integration. Voice portals, which provide a speech-based interface between a telephone user and Web-based services, are the most recent application of spoken dialogue technology. This article describes the main components of the technology-speech recognition, language understanding, dialogue management, communication with an external source such as a database, language generation, speech synthesis-and shows how these component technologies can be integrated into a spoken dialogue system. The article describes in detail the methods that have been adopted in some well-known dialogue systems, explores different system architectures, considers issues of specification, design, and evaluation, reviews some currently available dialogue development toolkits, and outlines prospects for future development." Year=2002} @Article{mehler2002, Author="{Mehler, A.}", Title="{Components of a model of context-sensitive hypertexts}", Journal="Journal of Universal Computer Science", Volume=8, Number=10, Pages="924-943", Abstract="On the background of rising Intranet applications the automatic generation of adaptable, context-sensitive hypertexts becomes more and more important [El-Beltagy et al., 2001]. This observation contradicts the literature on hypertext authoring, where Information Retrieval techniques prevail, which disregard any linguistic and context-theoretical underpinning. As a consequence, resulting hypertexts do not manifest those schematic structures, which are constitutive for the emergence of text types and the context-mediated understanding of their instances, i.e. natural language texts. This paper utilizes Systemic Functional Linguistics (SFL) and its context model as a theoretical basis of hypertext authoring. So called Systemic Functional Hypertexts (SFHT) are proposed, which refer to a stratified context layer as the proper source of text linkage. The purpose of this paper is twofold: First, hypertexts are reconstructed from a linguistic point of view as a kind of supersign, whose constituents are natural language texts and whose structuring is due to intra- and intertextual coherence relations and their context-sensitive interpretation. Second, the paper prepares a formal notion of SFHTs as a first step towards operationalization of fundamental text linguistic concepts. On this background, SFHTs serve to overcome the theoretical poverty of many approaches to link generation." Year=2002} @InProceedings{mellish-etal98, Author="{Mellish, Chris and Knott, Alistair and Oberlander, Jon and O'Donnell, Michael}", Title="{Experiments using stochastic search for text planning}", Booktitle="Proceedings of ACL Workshop on Natural Language Generation", Address="Niagara-on-the-lake, Canada", Pages="98-107", Year=1998} @InProceedings{mentis-etal2009, Author="{Mentis, Helena M. and Bach, Paula M. and Hoffman, Blaine and Rosson, Mary Beth and Carroll, John M.}", Title="{Development of decision rationale in complex group decision making}", Booktitle="Proceedings of 27th Annual CHI Conference on Human Factors in Computing Systems", Address="Boston, MA", Pages="1341-1350", Year=2009} @InProceedings{meteer93, Author="{Meteer, Marie}", Title="{Assumptions underlying discourse relations: Which ones are really there and where are they?}", Booktitle="Proceedings of Workshop on Intentionality and Structure in Discourse Relations, ACL", Publisher="ACL", Address="Ohio State University", Pages="82-85", Year=1993} @Article{mey2006, Author="{Mey, J. L.}", Title="{Focus-on issue: The pragmatics of discourse management}", Journal="Journal of Pragmatics", Volume=38, Number=4, Pages="473-474", Year=2006} @InProceedings{miike-etal94, Author="{Miike, Seiji and Itoh, Etsuo and Ono, Kenji and Sumita, Kazuo}", Title="{A full-text retrieval system with a dynamic abstract generation function}", Booktitle="Proceedings of the 17th Annual International ACM-SIGIR Conference", Address="Dublin, Ireland", Pages="152-161", Year=1994} @Article{millis-just94, Author="{Millis, Keith K. and Just, Marcel A.}", Title="{The influence of connectives on sentence comprehension}", Journal="Journal of Memory and Language", Volume=33, Pages="128-147", Year=1994} @InProceedings{milosavljevic-oberlander98, Author="{Milosavljevic, Maria and Oberlander, Jon}", Title="{Dynamic Hypertext catalogues: Helping users to help themselves}", Booktitle="Proceedings of 9th ACM Conference on Hypertext and Hypermedia", Address="Pittsburgh, Pennsylvania", Pages="123-131", Year=1998} @InProceedings{miltsakaki-etal2003, Author="{Miltsakaki, Eleni and Creswell, Cassandre and Forbes, Kate and Joshi, Aravind K. and Webber, Bonnie Lynn}", Title="{Anaphoric arguments of discourse connectives: Semantic properties of antecedents versus non-antecedents}", Booktitle="Proceedings of the Computational Treatment of Anaphora Workshop (EACL-2003)", Address="Budapest, Hungary", Year=2003} @Article{miltsakaki-kukich2004, Author="{Miltsakaki, Eleni and Kukich, Karen}", Title="{Evaluation of text coherence for electronic essay scoring systems}", Journal="Natural Language Engineering", Volume=10, Number=1, Pages="25-55", Year=2004} @InProceedings{miltsakaki-etal-annotation2004, Author="{Miltsakaki, Eleni and Prasad, Rashmi and Joshi, Aravind K and Webber, Bonnie}", Title="{Annotating discourse connectives and their arguments}", Booktitle="Proceedings of the HLT/NAACL Workshop on Frontiers in Corpus Annotation", Address="Boston, MA", Year=2004} @Article{min2007, Author="{Min, Daihwan}", Title="{A survey on methods for analyzing team communication}", Journal="Journal of Information Technology Applications and Management", Volume=14, Number=2, Pages="169-187", Note="Citation of: - Taboada 2003 (Modeling task-oriented comm.) - Taboada 2004 (in Moder and Martinovic-Zic) - Taboada and Mann 2006 (both parts)", Year=2007} @Article{mizuta-etal2006, Author="{Mizuta, Y. and Korhonen, A. and Mullen, T. and Collier, N.}", Title="{Zone analysis in biology articles as a basis for information extraction}", Journal="International Journal of Medical Informatics", Volume=75, Number=6, Pages="468-487", Note="Cited References: CARLSON L, P 2 SIGDIAL WORKSH D CRAVEN M, 1999, P 7 INT C INT SYST M, P77 HUMPHREYS K, 2000, PAC S BIOC, P505 KANDO N, 1999, P 4 INT WORKSH INF R, P126 LEHMAM A, 1999, INFORM PROCESS MANAG, V35, P181 LIDDY ED, 1991, INFORM PROCESS MANAG, V27, P55 MANN W, 1987, TEXT, V8, P243 MIZUTA Y, 2004, NII2004007E MIZUTA Y, 2004, P 4 INT C LANG EV LR, P1737 MIZUTA Y, 2004, P JOINT WORKSH NAT L, P29 PRASAD R, 2004, P ACL WORKSH DISC AN SWALES J, 1990, GENRE ANAL TANABE L, 2002, BIOINFORMATICS, V18, P1124 TAPANAINEN P, 1997, P 5 C APPL NAT LANG, P64 TEUFEL S, 2002, COMPUT LINGUIST, V28, P409 TEUFEL S, 2004, P 4 INT C LANG EV LR Article", Abstract="In the field of biomedicine, an overwhelming amount of experimental data has become available as a result of the high throughput of research in this domain. The amount of results reported has now grown beyond the limits of what can be managed by manual means. This makes it increasingly difficult for the researchers in this area to keep up with the latest developments. Information extraction (IE) in the biological domain aims to provide an effective automatic means to dynamically manage the information contained in archived journal articles and abstract collections and thus help researchers in their work. However, white considerable advances have been made in certain areas of IE, pinpointing and organizing factual information (such as experimental results) remains a challenge. In this paper we propose tackling this task by incorporating into IE information about rhetorical zones, i.e. classification of spans of text in terms of argumentation and intellectual attribution. As the first step towards this goat, we introduce a scheme for annotating biological texts for rhetorical zones and provide a qualitative and quantitative analysis of the data annotated according to this scheme. We also discuss our preliminary research on automatic zone analysis, and its incorporation into our IE framework. (c) 2005 Elsevier Ireland Ltd. All rights reserved." Year=2006} @Article{moens2007, Author="{Moens, Marie-Francine}", Title="{Summarizing court decisions}", Journal="Information Processing and Management", Volume=43, Number=6, Pages="1748-1764", Abstract="In the field of law there is an absolute need for summarizing the texts of court decisions in order to make the content of the cases easily accessible for legal professionals. During the SALOMON and MOSAIC(2) projects we investigated the summarization and retrieval of legal cases. This article presents some of the main findings while integrating the research results of experiments on legal document summarization by other research groups. In addition, we propose novel avenues of research for automatic text summarization, which we currently exploit when summarizing court decisions in the ACILA(3) project. Techniques for automated concept learning and argument recognition are here the most challenging. (C) 2007 Elsevier Ltd. All rights reserved." Year=2007} @Article{moens-debusser2002, Author="{Moens, Marie-Francine and De Busser, Rik}", Title="{First steps in building a model for the retrieval of court decisions}", Journal="International Journal of Human-Computer Studies", Volume=57, Number=5, Pages="429-446", Note="Cited Reference Count: 44 Cited References: ALLEN J, 1995, NATURAL LANGUAGE UND AMRCU D, 2000, THEORY PRACTICE DISC ASHLEY KD, 1990, MODELING LEGAL ARGUM ASHLEY KD, 1992, ARTIF INTELL, V1, P113 BASILI R, 2000, P MACH LEARN INF EXT BING J, 1987, LAW LIBR J, V79, P187 BRANTING LK, 2000, REASONING RULES PREC BRUNINGHAUS S, 1997, P 6 INT C ART INT LA, P123 BRUNINGHAUS S, 2001, CASE BASED REASONING BRUNNER MC, 1999, IMMUNOLOGIST, V7, P9 DICK JP, 1989, P 2 INT C ART INT LA, P244 FOX EA, 1999, MODERN INFORMATION R, P415 FUHR N, 2001, P 2J ANN INT ACM SIG GARDNER A, 1987, ARTIFICIAL INTELLIGE GROSZ B, 1986, COMPUTATIONAL LINGUI, V12, P175 HAFNER CD, 1987, P 1 INT C ART INT LA, P35 HAFNER CD, 1981, INFORMATION RETRIEVA HEARST MA, 1997, COMPUT LINGUIST, V23, P33 HOVY EH, 1993, ARTIF INTELL, V63, P341 HUNTER D, 1999, ARTIFICIAL INTELLIGN, V7, P129 KOLODNER J, 1993, CASE BASED REASONING LEDERER FI, 1996, P 1 EUR C LAW COMP A, P70 MANN WC, 1988, TEXT, V8, P243 MANN WC, 1992, DISCOURSE DESCRIPTIO, P39 MARCU D, 1997, THESIS U TORONTO CAN MATTHIJSSEN L, 2000, JURISPRUDENTIEDATABA MCCARTY LT, 1984, DATA PROCESSING LAW, P125 MOENS MF, 2001, P 24 ACM SIGIR ANN I, P418 MOENS MF, 1997, INFORM PROCESS MANAG, V33, P727 MOENS MF, 1999, J AM SOC INFORM SCI, V50, P151 MOENS MF, 1999, INT J HUM-COMPUT ST, V51, P1155 MOENS MF, 2001, ARTIF INTELL, V9, P29 MOORE JD, 1992, COMPUTATIONAL LINGUI, V18, P537 MOORE JD, 1993, COMPUTATIONAL LINGUI, V19, P651 RISSLAND EL, 1996, ARTIF INTELL, V4, P1 SALTON G, 1994, SCIENCE, V264, P1421 SODERLAND S, 1999, MACH LEARN, V34, P233 THOMPSON P, 2001, P 8 INT C ART INT LA, P70 UYTTENDAELE C, 1998, ARTIF INTELL, V6, P59 VANBELLE W, 1990, VAN EKSTANALYSE TEKS VANDIJK TA, 1997, DISCOURSE STRUCTURE, V1, P1 WEBER R, 1999, P 7 INT C ART INT LA, P164 WINKELS R, 2000, LEGAL KNOWLEDGE INFO, P85 ZELEZNIKOW J, 1995, P 5 INT C ART INT LA, P185 Article", Abstract="The MOSAIC project investigates a retrieval model for court decisions based on structured and unstructured (natural language) information in legal cases. This paper focuses on how relevant information in court decisions can function as a key for retrieval and on the automated construction of case representations. Techniques of automated concept learning and rhetorical structure identification are among the most promising ones. (C) 2002 Elsevier Science Ltd. All rights reserved." Year=2002} @Article{mohamed-omer99, Author="{Mohamed, Aysha H. and Omer, Marjzoub R.}", Title="{Syntax as a marker of rhetorical organization in written texts: Arabic and English}", Journal="International Review of Applied Linguistics in Language Teaching (IRAL)", Volume=37, Number=4, Pages="291-305", Abstract="Two Arabic stories & their English translations & two Arabic & English stories (unrelated by translation) were compared with reference to sentence organization, coordination, & subordination. This comparison showed that Arabic & English sentences are differently organized; coordination is more common in Arabic than in English, while subordination is more frequent in English than in Arabic. It is argued that these syntactic differences & their underlying semantic representations reflect differences at the higher level of rhetorical text organization. 4 Tables, 35 References. Adapted from the source document", Year=1999} @Article{mohamed-etal2008, Author="{Mohamed, M. T. and Clifton, C.}", Title="{Processing inferential causal statements: Theoretical refinements and the role of verb type}", Journal="Discourse Processes", Volume=45, Number=1, Pages="24-51", Abstract="An evidential causal relation like, "Because most distinguished students got bad grades, the teacher made some mistakes in evaluating his students' papers," is more difficult to process than a factual one like, "Because he got tired after a long semester, the teacher made some mistakes in evaluating his students' papers" (Noordman & de Blijzer, 2000; Traxler, Sanford, Aked, & Moxey, 1997). Two experiments explored the distinguishing characteristics of different types of causal relations. Experiment I introduced a third type of causal relation-a deductive causal relation-such as, "Because grading a paper is a subjective process, the teacher made some mistakes in evaluating his students' papers." Deductive causal relations are intermediate in difficulty between factual and evidential causal relations but behave in important ways like evidential relations. Experiment 2 found that using psychological verbs (e.g., like) to express evidential relations makes causal statements that express these relations more acceptable than their counterparts expressed using action verbs (e.g., destroy). The article concludes with a discussion of the main characteristics of different types of causal statements. It is argued that understanding the speaker's theory of mind is the basis for comprehending evidential and deductive causal relations. Finally, this article proposes a tentative framework for analyzing the comprehension of causal relations." Year=2008} @InCollection{molina-flores2006, Author="{Molina, M. and Flores, V.}", Title="{Generating adaptive presentations of hydrologic behavior}", BookTitle="Intelligent Data Engineering and Automated Learning - Ideal 2006, Proceedings", Series="Lecture Notes in Computer Science", Volume=4224, Pages="896-903", Abstract="This paper describes a knowledge-based approach for summarizing and presenting the behavior of hydrologic networks. This approach has been designed for visualizing data from sensors and simulations in the context of emergencies caused by floods. It follows a solution for event summarization that exploits physical properties of the dynamic system to automatically generate summaries of relevant data. The summarized information is presented using different modes such as text, 2D graphics and 3D animations on virtual terrains. The presentation is automatically generated using a hierarchical planner with abstract presentation fragments corresponding to discourse patterns, taking into account the characteristics of the user who receives the information and constraints imposed by the communication devices (mobile phone, computer, fax, etc.). An application following this approach has been developed for a national hydrologic information infrastructure of Spain." Year=2006} @InProceedings{mooney-etal90, Author="{Mooney, David and Carberry, Sandra and McCoy, Kathleen}", Title="{The basic block model of extended explanations}", Booktitle="Proceedings of 5th International Workshop on Natural Language Generation (IWNLG 5)", Address="Dawson, Pennsylvania", Pages="112-119", Year=1990} @Article{moore-mittal96, Author="{Moore, Johanna D and Mittal, Vibhu}", Title="{Dynamically generated follow-up questions}", Journal="Computer", Volume=29, Number=7, Pages="75-&", Abstract="Automatic text generators are at the heart of systems that provide users with information. The trick is getting the system to answer follow-up questions as naturally as possible. But even in moderately complex domains, the task of handcrafting explanations using ''canned'' text or templates is so time-consuming and error-prone that it becomes infeasible. Furthermore, these techniques cannot be extended to let a system consider the user's prior knowledge, past problem-solving experiences, or the preceding dialogue. To overcome these limitations, researchers have focused on automatically synthesizing text directly from underlying knowledge bases. Automatic text-generation systems pose new opportunities-and new problems. Studies of human-human interactions show that people often follow up requests for information with more questions. This observation also underscores the need for computer-based information systems to let users ask follow-up questions. This capability is especially crucial in patient education, for example, where misunderstandings could have serious consequences. The ability to handle follow-up requests in context is essential, even crucial, to applications like the patient education system described in this article. The direction we've taken presents one alternative to full-fledged natural language-understanding and makes it possible to design systems by adopting a pragmatic (and possibly more useful) approach of generating choices for the user. Our initial system evaluations reveal that users are comfortable with the interface as a way to ask follow-up questions." Year=1996} @Article{moore-paris93, Author="{Moore, Johanna D and Paris, Cécile}", Title="{Planning text for advisory dialogues: Capturing intentional and rhetorical information}", Journal="Computational Linguistics", Volume=19, Number=4, Pages="651-694", Abstract="Presentation of a text planner that not only tracks the rhetorical relations between parts of the text, but the intention effect of sections of the text upon the reader as well. Follows from the 1992 observation that both ideational and interpersonal information needs to be captured." Year=1993} @Article{moore-pollack, Author="{Moore, Johanna D and Pollack, Martha E}", Title="{A problem for RST: The need for multi-level discourse analysis}", Journal="Computational Linguistics", Volume=18, Number=4, Pages="537-544", Abstract="Claims that single RST relations are not sufficient. There are cases where both ideational and interpersonal relations hold between the same pieces of text, and both sets of information need to be captured." Year=1992} @Article{moreale-vargas-vera2004, Author="{Moreale, E. and Vargas-Vera, M.}", Title="{Semantic services in e-Learning: An argumentation case study}", Journal="Educational Technology & Society", Volume=7, Number=4, Pages="112-128", Abstract="This paper outlines an e-Learning services architecture offering semantic-based services to students and tutors, in particular ways to browse and obtain information through web services. Services could include registration, authentication, tutoring systems, smart question answering for students' queries, automated marking systems and a student essay service. These services - which might be added incrementally to the portal - could be integrated with various ontologies such as ontologies of educational organisations, students and courses. In this paper, we describe a few scenarios in the e-learning domain and illustrate the role of a few services. We also describe in some detail a service doing semantic annotation of argumentation in student essays for allowing visualization of argumentation and providing useful feedback to students." Year=2004} @InProceedings{mori96, Author="{Mori, Yoshiki}", Title="{Multiple discourse relations on the sentential level in Japanese}", Booktitle="Proceedings of 16th International Conference on Computational Linguistics (COLING'96)", Address="Copenhagen, Denmark", Pages="788-793", Year=1996} @Article{morris-finkelstein99, Author="{Morris, S. J. and Finkelstein, A. C. W.}", Title="{Engineering via discourse: Content structure as an essential component for multimedia documents}", Journal="International Journal of Software Engineering and Knowledge Engineering", Volume=9, Number=6, Pages="691-724", Abstract="Practical problems of multimedia document production require software engineers to provide an effective framework for inter-professional work. This paper distinguishes between abstract and physical media and hence provides the basis for definitions of multiple media and multimedia and the context for reviewing content structures proven in other disciplines. Such structures can act as a guide for production and the notion of the navigable discourse structure provides the essential means for testing content design. Combining these structures in a discourse driven process model and production method facilitates both the design of content and the development of associated software in an ordered and integrated manner, thus avoiding the pitfalls of ad hoc approaches. Investigation and testing of these concepts was effected via two case studies involving the production of two multimedia demonstrations of software engineering tools." Year=1999} @InProceedings{moser-moore95, Author="{Moser, Megan and Moore, Johanna D}", Title="{Using discourse analysis and automatic text generation to study discourse cue usage}", Booktitle="Proceedings of AAAI Spring Symposium on Empirical Methods in Discourse Interpretation and Generation", Address="Stanford, California", Pages="92-98", Year=1995} @InProceedings{moser-moore95b, Author="{Moser, Megan and Moore, Johanna D}", Title="{Investigating cue selection and placement in tutorial discourse}", Booktitle="Proceedings of 33rd Annual Meeting of the Association for Computational Linguistics (ACL'95)", Address="Cambridge, Massachusetts", Pages="130-135", Year=1995} @Article{moser-moore96, Author="{Moser, Megan and Moore, Johanna D}", Title="{Towards a synthesis of two accounts of discourse structure}", Journal="Computational Linguistics", Volume=22, Number=3, Pages="410-419", Abstract="Presents Intentional Linguistic Strucutre, a theory-neutral term for the intentional relations in a text. This is used to lay out the common ground between G&S and RST, showing the possibilities of synthesis. This most likely relates back to RDA, but never seems to have moved forward." Year=1996} @Article{muntigl-gruber2005, Author="{Muntigl, Peter and Gruber, Helmut}", Title="{Introduction: Approaches to genre}", Journal="Folia Linguistica", Volume=39, Number=1-2, Pages="1-18", Abstract="Nice summary of German approaches to genre", Year=2005} @InProceedings{murray-etal2006, Author="{Murray, Gabriel and Taboada, Maite and Renals, Steve}", Title="{Prosodic correlates of rhetorical relations}", Booktitle="Proceedings of HLT-NAACL 2006 Workshop on "Analyzing Conversations in Text and Speech"", Address="New York", Pages="1-7", Year=2006} @Article{myers-etal87, Author="{Myers, Jerome L. and Shinjo, Makiko and Duffy, Susan A}", Title="{Degree of causal relatedness and memory}", Journal="Journal of Memory and Language", Volume=26, Number=4, Pages="453-465", Abstract="J. M. Keenan, S. D. Baillet, and P. Brown ((1984) Journal of Verbal Learning and Verbal Behavior, 23, 115–126) varied the causal relation between two sentences in passages read by their subjects. Subsequent recall of one sentence cued by the other improved, and then deteriorated as the causal relatedness of the two sentences increased. The present experiments extended this work and replicated the basic finding of a quadratic relation between recall and causal relatedness. Several explanations are considered to account for these results. The long reading times together with relatively poor recall at low levels of causal relatedness argue against a pure processing effort model. Variations in the integration and elaboration of the representation of the sentence pairs would seem to better account for the relation of recall and causal relatedness. Several issues raised by this explanation are then briefly considered." Year=1987} @InProceedings{nakano-kato98, Author="{Nakano, Yukiko and Kato, Tsuenaki}", Title="{Cue phrase selection in instruction dialogue using machine learning}", Booktitle="Proceedings of COLING-ACL Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="100-106", Year=1998} @Article{neff-etal2008, Author="{Neff, M. and Kipp, M. and Albrecht, I. and Seidel, H. P.}", Title="{Gesture modeling and animation based on a probabilistic re-creation of speaker style}", Journal="Acm Transactions on Graphics", Volume=27, Number=1, Abstract="Animated characters that move and gesticulate appropriately with spoken text are useful in a wide range of applications. Unfortunately, this class of movement is very difficult to generate, even more so when a unique, individual movement style is required. We present a system that, with a focus on arm gestures, is capable of producing full-body gesture animation for given input text in the style of a particular performer. Our process starts with video of a person whose gesturing style we wish to animate. A tool-assisted annotation process is performed on the video, from which a statistical model of the person's particular gesturing style is built. Using this model and input text tagged with theme, rheme and focus, our generation algorithm creates a gesture script. As opposed to isolated singleton gestures, our gesture script specifies a stream of continuous gestures coordinated with speech. This script is passed to an animation system, which enhances the gesture description with additional detail. It then generates either kinematic or physically simulated motion based on this description. The system is capable of generating gesture animations for novel text that are consistent with a given performer's style, as was successfully validated in an empirical user study." Year=2008} @PhDThesis{nicholas94, Author="Nicholas, Nick", Title="{Problems in the Application of Rhetorical Structure Theory to Text Generation}", School="University of Melbourne", Type="Master's thesis", Year=1994} @Article{nicholas95, Author="{Nicholas, Nick}", Title="{Parameters for Rhetorical Structure Theory ontology}", Journal="University of Melbourne Working Papers in Linguistics", Volume=15, Pages="77-93", Abstract="Discusses the application of the Sanders Spooren Noordman 1992 relational criterion to temportal relations, then covers the broader impact of this on the set of relations used in RST. Overall looking to decide what relations belong in the framwork and the granularity of relation specification", Year=1995} @Article{nir-berman2010, Author="{Nir, Bracha and Berman, Ruth A.}", Title="{Complex syntax as a window on contrastive rhetoric}", Journal="Journal of Pragmatics", Volume=42, Number=3, Pages="744-765", Note="Citation of Taboada and Mann 2006, part 1", Abstract="The paper concerns complex syntax in the sense of text-embedded clause-combining. We consider different perspectives on why languages employ complex syntax, taking the usage-based view that “discourse drives grammar”. Complex syntax is analyzed as shedding light on the nature of “contrastive rhetoric”, on the assumption that linguistic typology interacts with rhetorical strategies in the construction of discourse. An innovative methodology is delineated for evaluating syntactic complexity along a hierarchy of clause-combining relations, from isotactic single clauses to paratactic symmetric and asymmetric stringing by coordination and complementation, on to hypotactic layering by adverbials and relative clauses, and endotactic nesting or embedding of one clause inside another. Detailed criteria for each of these levels of clause-combining were applied to 64 narrative texts written by graduate-level university students, native speakers of four different languages (English, French, Hebrew, and Spanish) on the shared topic of interpersonal conflict. The discourse effects of linguistic typology are analyzed in terms of the linguistic means available to these different languages for combining clauses as well as discursive strategies preferred by speaker–writers in constructing narratives." Year=2010} @PhDThesis{nomoto2004, Author="Nomoto, Tadashi", Title="{Machine Learning Approaches to Rhetorical Parsing and Open-Domain Text Summarization}", School="Nara Institute of Science and Technology", Type="Ph.D. dissertation", Year=2004} @InProceedings{nomoto-matsumoto99, Author="{Nomoto, Tadashi and Matsumoto, Yuji}", Title="{Learning discourse relations with active data selection}", Booktitle="Proceedings of Joint ACL-SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora", Address="College Park, Maryland", Pages="158-167", Year=1999} @InCollection{noordman-etal99, Author="{Noordman, Leo and Dassen, Ingrid and Swerts, Mar and Terken, Jacques}", Title="{Prosodic markers of text structure}", BookTitle="Discourse Studies in Cognitive Linguistics: Selected Papers from the Fifth International Cognitive Linguistics Conference", Editor="van Hoek, Karen and Kibrik, Andrej A. and Noordman, Leo", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="131-148", Year=1999} @Article{noordman-vonk92, Author="{Noordman, Leo and Vonk, W.}", Title="{Readers knowledge and the control of inferences in reading}", Journal="Language and Cognitive Processes", Volume=7, Number=3-4, Pages="373-391", Abstract="There is a consensus in the literature that inferences which contribute to the coherence of the text representation are made during reading. This study demonstrates that this is an over-generalisation and that one has to make a distinction between relations internal to the structure of the representation and relations that involve reference to the world. It is demonstrated that the reader's knowledge of the world is an important factor in controlling inferences. A number of experiments are discussed in which the role of the reader's knowledge with respect to the information to be inferred is investigated by varying the materials in terms of their familiarity to the reader, and by having readers with high and low knowledge with respect to the content domain of the text." Year=1992} @Article{noordman-etal92, Author="{Noordman, Leo and Vonk, W. and Kempff, H.}", Title="{Causal inferences during the reading of expository texts}", Journal="Journal of Memory and Language", Volume=31, Pages="573-590", Year=1992} @InProceedings{not96, Author="{Not, Elena}", Title="{A computational model for generating referring expressions in a multilingual application domain}", Booktitle="The 16th International Conference on Computational Linguistics (COLING'96)", Address="Copenhagen, Denmark", Pages="848-853", Year=1996} @InProceedings{not-zancaro2000, Author="{Not, Elena and Zancanaro, Massimo}", Title="{The MacroNode approach: Mediating between adaptive and dynamic hypermedia}", Booktitle="International Conference on Adaptive Hypermedia and Web-Based Systems", Address="Trento, Italy", Pages="166-178", Year=2000} @TechReport{oates99, Author="{Oates, Sarah Louise}", Title="{State of the Art Report on Discourse Markers and Relations}", Institution="University of Brighton, Information Technology Research Institute", Abstract="Summarises previous work on discourse markers, and existing models of discourse representation, including G&S, RST, and extensions to 2, 3, and 4 levels of representation. Also touches on the generation of markers." Year=1999} @InProceedings{oates2000, Author="{Oates, Sarah Louise}", Title="{Multiple discourse marker occurrence: Creating hierarchies for Natural Language Generation}", Booktitle="ANLP-NAACL 2000 Student Research Workshop", Address="Seattle, Washington", Pages="41-45", Year=2000} @TechReport{oberlander-mellish98, Author="{Oberlander, Jon and Mellish, Chris}", Title="{Final Report on the ILEX Project}", Institution="Division of Informatics, University of Edinburgh", Note="This was a web-published paper, but the site seems to have been lost in a fire." Abstract="Presents a brief summary of all the stages and developments made during the course of the ILEX project. Includes a bibliography of ILEX-related papers." Year=1998} @InProceedings{oberlander-moore99, Author="{Oberlander, Jon and Moore, Johanna D}", Title="{Cue phrases in discourse: Further evidence for the core:Contributor distinction}", Booktitle="Workshop on Levels of Representation in Discourse", Address="Edinburgh, UK", Pages="87-93", Year=1999} @Article{oberlander-moore2001, Author="{Oberlander, Jon and Moore, Johanna D}", Title="{Discourse cues: Further evidence for the core-contributor distinction}", Journal="Cognitive Linguistics", Volume=12, Number=3, Pages="317-332", Note="Cited Reference Count: 17 Cited References: ALTMANN G, 1988, COGNITION, V30, P191 ELHADAD M, 1990, P COLING90, V3, P97 GROSZ B, 1986, COMPUTATIONAL LINGUI, V12, P175 GROSZ BJ, 1995, COMPUT LINGUIST, V21, P203 HOBBS JR, 1985, CSLI-8537 CTR STUD L LESGOLD AM, 1992, INTELLIGENT TUTORING, P201 MANN WC, 1988, TEXT, V8, P243 MOSER M, 1995, P 33 ANN M ASS COMP, P130 MOSER M, 1996, COMPUT LINGUIST, V22, P409 MOSER M, IN PRESS DISCOURSE P NORRDMAN LGM, 2001, TEXT REPRESENTATION, P153 OBERLANDER J, 1998, COMPUT LINGUIST, V24, P501 POLANYI L, 1988, PRAGMATICS, V12, P601 REDEKER G, 1990, J PRAGMATICS, V14, P367 SPOOREN W, 1989, THESIS KATHOLIEKE U STEVENSON R, 1995, P 17 ANN C COGN SCI, P328 STEVENSON R, 2000, LANG COGNITIVE PROC, V15, P225 Article", Abstract="Moser and Moore (1995, to appear) carried out a corpus study of discourse cues in tutorial dialogue. Their annotation uses Relational Discourse Analysis (RDA), which distinguishes core elements (nuclei-like) from contributors (satellite-like). In their discussion of these results, Moser and Moore propose that clauses in the contributor-core order are harder to understand than clauses in core-contributor order, but do not attempt to explain why the "hard" order is ever used. Here, we recruit evidence from work by Stevenson and her collaborators, which substantiates the empirical claim. We then suggest that by distinguishing information structure (given-new) from intentional structure (core-contributor), we can explain why hard orders are surprisingly frequent. We not, however, that this cannot be the whole story, and show how the hierarchical RDA structure helps account for differences between discourse cues such as since, so, this means, and therefore." Year=2001} @Article{obrien95, Author="{O'Brien, Theresa}", Title="{Rhetorical structure analysis and the case of the inaccurate, incoherent source-hopper}", Journal="Applied Linguistics", Volume=16, Number=4, Pages="442-482", Abstract="Presents a comparison of a take-home essay and an examination essay written by the same student on the same topic six weeks apart using RST. A contrast is shown between the adequate handling of material in memory under examination conditions leading to a coherent text vs. the uncertain handling of difficult source material leading to an incoherent almost incomprehensible take-home essay." Year=1995} @InProceedings{odonnell-rsttool97, Author="{O'Donnell, Michael}", Title="{RST-Tool: An RST analysis tool}", Booktitle="Proceedings of the 6th European Workshop on Natural Language Generation", Address="Duisburg, Germany", Year=1997} @InProceedings{odonnell2000, Author="{O'Donnell, Michael}", Title="{RSTTool 2.4: A markup tool for Rhetorical Structure Theory}", Booktitle="First International Conference on Natural Language Generation (INLG'2000)", Address="Mitzpe Ramon, Israel", Pages="253-256", Year=2000} @InProceedings{odonnell-etal98, Author="{O'Donnell, Michael and Cheng, Hua and Hitzeman, Janet}", Title="{Integrating referring and informing in NP planning}", Booktitle="Proceedings of COLING-ACL Workshop on The Computational Treatment of Nominals", Address="Montréal, Canada", Pages="46-55", Year=1998} @Article{odonnell-etal2001, Author="{O'Donnell, Michael and Mellish, Chris and Oberlander, Jon and Knott, Alistair}", Title="{ILEX: An architecture for a dynamic Hypertext generation system}", Journal="Natural Language Engineering", Volume=7, Pages="225-250", Abstract="Presents the architecture of ILEX, describing along the way how the system was formed by the specific demands of generating hypertext, as opposed to traditional text-generation systems." Year=2001} @InProceedings{oishi-matsumoto98, Author="{Oishi, Akira and Matsumoto, Yuji}", Title="{Recognition of the coherence relation between te-linked clauses}", Booktitle="Proceedings of 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (COLING-ACL'98)", Address="Montréal, Canada", Pages="990-996", Year=1998} @InCollection{okazaki-etal2004, Author="{Okazaki, N. and Matsuo, Y. and Ishizuka, M.}", Title="{Coherent arrangement of sentences extracted from multiple newspaper articles}", BookTitle="Pricai 2004: Trends in Artificial Intelligence, Proceedings", Series="Lecture Notes in Artificial Intelligence", Volume=3157, Pages="882-891", Abstract="Multi-document summarization is a challenge to information overload problem to provide a condensed text for a number of documents. Most multi-document summarization systems make use of extraction techniques (e.g., important sentence extraction) and compile a summary from the selected information. However, sentences gathered from multiple sources are not organized as a comprehensible text. Therefore, it is important to consider sentence ordering of extracted sentences in order to reconstruct discourse structure in a summary. We propose a novel method to plan a coherent arrangement of sentences extracted from multiple newspaper articles. Results of our experiment show that sentence reordering has a discernible effect on summary readability. The results also shows significant improvement on sentence arrangement compared to former methods." Year=2004} @PhDThesis{olson81, Author="Olson, Michael L." Title="{Barai Clause Junctures: Toward a Functional Theory of Interclausal Relations}", School="Australian National University", Type="PhD dissertation", Year=1981} @InProceedings{ono-etal94, Author="{Ono, Kenji and Sumita, Kazuo and Miike, Seiji}", Title="{Abstract generation based on rhetorical structure extraction}", Booktitle="Proceedings of 15th International Conference on Computational Linguistics (COLING'94)", Address="Kyoto, Japan", Pages="344-348", Year=1994} @InProceedings{otterbacher-etal2002, Author="{Otterbacher, Jahna and Radev, Dragomir and Luo, Airong}", Title="{Revisions that improve cohesion in multi-document summaries: A preliminary study}", Booktitle="Proceedings of ACL Workshop on Automatic Summarization", Address="Philadelphia, Pennsylvania", Pages="27-36", Year=2002} @InCollection{ou-etal2003, Author="{Ou, S. Y. and Khoo, C. S. G. and Goh, D. H.}", Title="{Multi-document summarization of dissertation abstracts using a variable-based framework}", BookTitle="Asist 2003: Proceedings of the 66th Asist Annual Meeting, Vol 40, 2003", Series="Proceedings of the Asist Annual Meeting", Volume=40, Pages="230-239", Abstract="This paper reports initial work on developing a method for automatic construction of multi-document summaries of sets of domain-specific dissertation abstracts. A variable-based framework for multi-document summarization of dissertation abstracts in the field of sociology and psychology that makes use of the macro-level and micro-level discourse structure of dissertation abstracts as well as cross-document structure is proposed. The micro-level structure of problem statements found in a sample of 50 dissertation abstracts was analyzed, and the common features found are described. A list of indicator phrases that denote different aspects of the problem statements is provided." Year=2003} @Article{ou-etal2006, Author="{Ou, S. Y. and Khoo, C. S. G. and Goh, D. H.}", Title="{Multi-document summarization of news articles using an event-based framework}", Journal="Aslib Proceedings", Volume=58, Number=3, Pages="197-217", Abstract="Purpose - The purpose of this research is to develop a method for automatic construction of multi-document summaries of sets of news articles that might be retrieved by a web search engine in response to a user query. Design/methodology/approach - Based on the cross-document discourse analysis. an event-based framework is proposed for integrating and organizing information extracted from different news articles. It has a hierarchical structure in which the summarized information is presented at the top level and more detailed information given at the lower levels. A tree-view interface was implemented for displaying a multi-document summary based on the framework. A preliminary user evaluation was performed by comparing the framework-based summaries against the sentence-based summaries. Findings - In a small evaluation. all the human subjects preferred the framework-based summaries to the sentence-based summaries. It indicates that the event-based framework is ail effective way to summarize a set of news articles reporting an event or a series of relevant events. Research limitations/implications - Limited to event-based news articles only, not applicable to news critiques and other kinds of news articles. A summarization system based on the event-based framework is being implemented. Originality/value - An event-based framework for summarizing sets of news articles was developed and evaluated using a tree-view interface for displaying Such summaries." Year=2006} @Article{maat98, Author="{Pander Maat, Henk}", Title="{Classifying negative coherence relations on the basis of linguistic evidence}", Journal="Journal of Pragmatics", Volume=30, Number=2, Pages="177-204", Abstract="Provides a corpus study of the distribution of seven Dutch negative connectives over relational classes, leading to a proposed revision to the relational classification proposed by Sanders etal earlier in the decade. ABSTRACT FROM SOURCE: This article proposes to revise the Sanders et al. (1992, 1993) classification of negative coherence relations on the basis of a comparative, corpus-based analysis of seven Dutch connectives. First, some conceptual problems in the Sanders et al. classification are discussed, with special attention for the 'polarity' parameter that distinguishes between 'positive' and 'negative' relations: Subsequently, a methodological section reviews different kinds of evidence for relation classifications. It is argued that the behavior of linguistic devices for the expression of coherence relations constitutes a crucial source of evidence and it is proposed to use a Discriminating Connective Principle when assessing this linguistic evidence. By means of a corpus study, it is shown that several refinements of the Sanders et al. classification are conceivable. In the revised framework, comparative relations take the place of additive relations, direct and indirect comparisons are distinguished and epistemic negative relations are further differentiated on the basis of the configuration of perspectives in the successive discourse segments. The linguistic support for the revised classification, as provided by the distribution of seven Dutch negative connectives over the relational classes, is shown to be satisfactory." Year=1998} @Article{pander-maat99, Author="{Pander Maat, H.}", Title="{The differential linguistic realization of comparative and additive coherence relations}", Journal="Cognitive Linguistics", Volume=10, Number=2, Pages="147-184", Abstract="it is commonly assumed that comparative coherence relations (e.g., Peter is tall but his brother is short) can be analyzed in terms of semantic contrast. In this article it is claimed that comparative relations need to be understood in a context containing a similarity assumption. This assumption may be confirmed (positive polarity) or denied (negative polarity) by the comparative text passage. When two entities are characterized in terms of a common variable without a similarity assumption being present (e.g., Peter's favorite color is red. His brother prefers green), the coherence relation is merely additive. Additive relations are not defined for polarity. While comparative relations may be linguistically marked by connectives like 'but', 'by contrast', or 'and' in English or 'maar', daarentegen', or 'en' in Dutch, additive relations remain unmarked. The distinction between comparative and additive relations is empirically supported by a corpus-based study of the linguistic marking of similarities and differences between the price movements of shares, using 400 fragments from stock-market reports in a Dutch daily newspaper. Some of these fragments clearly invoke similarity assumptions, for instance because of the fact that two companies are in the same branch of industry or because the fragment is preceded by an announcement of the general trend in share prices on a particular day. It was found that the overwhelming majority of linguistic markers of similarities and differences in share price movements occurred in contexts containing similarity assumptions. For instance, similarities that were to be expected may be marked by 'en', 'and' (e.g. Elsevier gained 1.10 [new price 67.80} [Daarentegen] Kluwer lost forty cents (new price 50.70)). Some apparent counterexamples, in which two companies from he same branch of industry show different share price movements while this difference remains unmarked, in fact do not invalidate the similarity assumption framework but support it. In the majority of these cases the similarity assumption has been eliminated or weakened by earlier announcements of difference within a certain branch. A closer analysis of five Dutch comparative connectives reveals that two dimensions of comparative polarity need to be distinguished: a propositional polarity parameter with the values 'difference' and 'similarity', and an assumptional polarity parameter distinguishing between confirmations and denials of the relevant assumption. Different linguistic elements may be characterize in terms of different polarity dimensions. For instance, 'ook', 'also', expresses positive propositional polarity, while 'maar', 'but', is an indication of negative assumptional polarity." Year=1999} @Article{pandermaat-degand2001, Author="{Pander Maat, Henk and Degand, Liesbeth}", Title="{Scaling causal relations and connectives in terms of speaker Involvement}", Journal="Cognitive Linguistics", Volume=12, Number=3, Pages="211-245", Year=2001} @Article{pandermaat-sanders2001, Author="{Pander Maat, Henk and Sanders, Ted}", Title="{Subjectivity in causal connectives: An empirical study of language in use}", Journal="Cognitive Linguistics", Volume=12, Number=3, Pages="247-273", Abstract="The linguistic categories apparent in people's everyday language use provide us with interesting insights into the working of the mind. In this article we study the way in which Dutch speakers categorize causally related events by expressing them with the connectives dus `so' or daarom `that's why'. These two connectives both express volitional and epistemic causal coherence relations. Their overlapping contexts of use raise the question of why two separate, highly grammaticalized linguistic items exist to express similar relationships. We propose an analysis of these connectives, clarifying their similarities and di.erences, in terms of subjectivity: the amount of speaker involvement. Empirical support for this analysis is presented from corpus studies and experiments in which language users were asked to state their preference for one of the connectives in contexts displaying different degrees of subjectivity." Year=2001} @InProceedings{pardo-nunes2006, Author="{Pardo, Thiago Alexandre Salgueiro and Nunes, Maria das Gracas Volpe}", Title="{Review and evaluation of DiZer - An automatic discourse analyzer for Brazilian Portuguese}", Booktitle="Proceedings of the 7th Workshop on Computational Processing of Written and Spoken Portuguese – PROPOR", Address="Rio de Janeiro-RJ, Brazil", Pages="180-189", Year=2006} @InProceedings{pardo-etal2004, Author="{Pardo, Thiago Alexandre Salgueiro and Nunes, Maria das Gracas Volpe and Rino, Lucia Helena Machado}", Title="{DiZer: An automatic discourse analyzer for Brazilian Portuguese}", Booktitle="Proceedings of First International Workshop on Natural Language Understanding and Cognitive Science (NLUCS 2004)", Address="Porto, Portugal", Year=2004} @InProceedings{pardo-rino2001, Author="{Pardo, Thiago Alexandre Salgueiro and Rino, Lucia Helena Machado}", Title="{A summary planner based on a three-level discourse model}", Booktitle="Proceedings of Natural Language Processing Pacific Rim Symposium", Address="Tokyo, Japan", Pages="533-538", Year=2001} @InProceedings{pardo-rino2002, Author="{Pardo, Thiago Alexandre Salgueiro and Rino, Lucia Helena Machado}", Title="{DMSumm: Review and assessment}", Booktitle="Proceedings of Advances in Natural Language Processing, Third International Conference (PorTAL 2002)", Publisher="Springer", Address="Faro, Portugal", Pages="263-274", Year=2002} @Article{paris2002, Author="{Paris, Cécile}", Title="{Information delivery for tourism}", Journal="Ieee Intelligent Systems", Volume=17, Number=6, Pages="61-63", Year=2002} @InProceedings{paris-scott94, Author="{Paris, Cécile and Scott, Donia}", Title="{Intentions, structure, and expression in multi-lingual instructions}", Booktitle="Proceedings Seventh International Conference on Natural Language Generation", Address="Kennebunkport, ME", Pages="45-52", Year=1994} @InCollection{paris-etal2001, Author="{Paris, Cécile and Wan, S. and Wilkinson, R. and Wu, M. F.}", Title="{Generating personal travel guides - And who wants them?}", BookTitle="User Modeling 2001, Proceedings", Series="Lecture Notes in Artificial Intelligence", Volume=2109, Pages="251-253", Abstract="In this paper we describe a system that generates synthesized web pages as a travel guide through integrating a discourse planner with a document retrieval system. We then present our investigation on whether the guide generated by such a system is actually preferred by users over a more general guide." Year=2001} @InCollection{paris-etal2004, Author="{Paris, Cécile and Wu, M. F. and Vander Linden, Keith and Post, M. and Lu, S. J.}", Title="{Myriad: An architecture for contextualized information retrieval and delivery}", BookTitle="Adaptive Hypermedia and Adaptive Web-Based Systems, Proceedings", Series="Lecture Notes in Computer Science", Volume=3137, Pages="205-214", Abstract="Users' information needs are largely driven by the context in which they make their decisions. This context is dynamic. It includes the users' characteristics, their current domain of application, the tasks they commonly perform and the device they are currently using. This context is also evolving. When one information need is satisfied, another is likely to emerge. An information access system must, therefore, be able to track this dynamic and evolving context, and exploit it to retrieve actionable information from appropriate sources and deliver it in a form suitable for the current situation. This paper presents a generic architecture that supports the construction of information retrieval and delivery systems that make use of context. The architecture, called Myriad, includes an adaptive virtual document planner, and explicit, dynamic representations of the user's current context." Year=2004} @Article{passonneau-litman97, Author="{Passonneau, Rebecca and Litman, Diane J.}", Title="{Discourse segmentation by human and automated means}", Journal="Computational Linguistics", Volume=23, Number=1, Pages="103-139", Note="Cited Reference Count: 72 Cited References: ABNEY SP, 1990, P 6 NEW OED C EL TEX, P1 ANDERSON AH, 1991, LANG SPEECH, V34, P351 AONE C, 1995, P 33 ANN M ASS COMP, P122 BRIEMAN L, 1984, CLASSIFICATION REGRE BUTTERWORTH B, 1980, LANGUAGE PRODUCTION, P155 CARBERRY S, 1990, PLAN RECOGNITION NAT CARLETTA J, 1996, COMPUT LINGUIST, V22, P249 CHAFE WL, 1980, PEAR STORIES COCHRAN WG, 1950, BIOMETRIKA, V37, P256 COHEN R, 1984, 10TH P INT C COMP LI, P251 DALE R, 1992, GENERATING REFERRING DUNCAN S, 1977, FACE FACE INTERACTIO FLAMMIA G, 1995, EUROSPEECH 1995 GALE W, 1992, P 30 ACL, P249 GROSZ B, 1986, COMPUTATIONAL LINGUI, V12, P175 GROSZ B, 1992, P INT C SPOK LANG PR GROSZ BJ, 1995, COMPUT LINGUIST, V21, P203 GROSZ BJ, 1977, THESIS U CALIFORNIA HEARST MA, 1994, P 32 ANN M ASS COMP, P9 HEARST MA, 1993, 9324 U CAL SEQ 2000 HINDLE D, 1983, 21ST P ANN M ASS COM, P123 HIRSCHBERG J, 1993, COMPUTATIONAL LINGUI, V19, P501 HIRSCHBERG J, 1991, P 2 EUR C SPEECH COM HIRSCHBERG J, 1996, P 34 ANN M ASS COMP, P286 HIRSCHBERG J, 1990, P 8 NAT C ART INT AA, P952 HIRSCHBERG J, 1986, 24TH P ANN M ASS COM, P136 HOBBS JR, 1979, COGNITIVE SCI, V3, P67 HWANG CH, 1992, 30TH P M ASS COMP LI, P232 ISARD A, 1995, AAAI 1995 SPR S SER, P60 KOZIMA H, 1993, P 31 ANN M STUD SESS, P286 KRIPPENDORFF K, 1980, CONTENT ANAL LEVY E, 1984, THESIS U CHICAGO LEWIS DD, 1994, P 11 INT C MACH LEAR, P148 LINDE C, 1979, SYNTAX SEMANTICS DIS, P337 LITMAN D, 1995, AAAI SPRING S SER EM, P85 LITMAN DJ, 1990, INTENTIONS COMMUNICA LITMAN DJ, 1996, J ARTIF INTELL RES, V5, P53 LITMAN DJ, 1994, P 12 NAT C ART INT A, P806 LITMAN DJ, 1995, P 33 ANN M ASS COMP, P108 MANN WC, 1988, TEXT, V8, P243 MARSLENWILSON W, 1982, SPEECH PLACE ACTION, P339 MOKROS HB, 1984, THESIS U CHICAGO MOORE JD, 1992, COMPUTATIONAL LINGUI, V18, P537 MOORE JD, 1993, COMPUTATIONAL LINGUS, V19, P652 MORRIS J, 1991, COMPUTATIONAL LINGUI, V17, P21 MOSER M, 1995, P 33 ANN M ASS COMP, P130 MOSER M, 1995, 9617 U PITTSB DEP CO NAKATANI CH, 1995, SPR S SER SMP METH D, P106 PASSONNEAU RJ, 1993, CHALLENGES NATURAL L PASSONNEAU RJ, 1996, COMPUTATIONAL CONVER PASSONNEAU RJ, 1996, LANG SPEECH 2-3, V39, P229 PASSONNEAU RJ, 1993, P 31 ANN M ASS COMP, P148 PASSONNEAU RJ, 1994, PROTOCOL CODING DISC PIERREHUMBERT J, 1987, 1122587032507 TM ATT PITRELLI J, 1994, P ICSLP POLANYI L, 1988, J PRAGMATICS, V12, P601 QUINLAN JR, 1993, C4 5 PROGRAMS MACHIN REICHMAN R, 1985, GETTING COMPUTERS TA REYNAR JC, 1994, P 32 ANN M STUD SESS, P331 ROTONDO JA, 1984, DISCOURSE PROCESS, V7, P69 SONG F, 1991, P 9 NAT C ART INT, P131 STIFLEMAN LJ, 1995, AAAI 1995 SPR S SER, P162 SWERTS M, 1995, ESCA WORKSH SPOK DIA, P205 SWERTS M, 1995, P 12 INT C PHON SCI, V4, P208 WALKER M, 1990, 28TH P ANN M ASS COM, P70 WALKER MA, 1995, COMPUTATIONAL LINGUI, V22, P255 WEBBER BL, 1988, COMPUTATIONAL LINGUI, V14, P113 WEBBER BL, 1991, LANG COGNITIVE PROC, P107 WEISS SM, 1991, COMPUTER SYSTEMS LEA WHITTAKER S, 1988, 26TH P ANN M ASS COM, P123 WIGHTMAN CW, 1994, IEEE T SPEECH AUDIO, V2, P469 YOUMANS G, 1991, LANGUAGE, V67, P763 Article", Abstract="The need to model the relation between discourse structure and linguistic features of utterances is almost universally acknowledged in the literature on discourse. However, there is only weak consensus on what the units of discourse structure are, or the criteria for recognizing and generating them. We present quantitative results of a two-part study using a corpus of spontaneous, narrative monologues. The first part of our paper presents a method for empirically validating multiutterance units referred to as discourse segments. We report highly significant results of segmentations performed by naive subjects, where a commonsense notion of speaker intention is the segmentation criterion. In the second part of our study, data abstracted from the subjects' segmentations serve as a target for evaluating two sets of algorithms that use utterance features to perform segmentation. On the first algorithm set, we evaluate and compare the correlation of discourse segmentation with three types of linguistic cues (referential noun phrases, cue words, and pauses). We then develop a second set using two methods: error analysis and machine learning. Testing the new algorithms on a new data set shows that when multiple sources of linguistic knowledge are used concurrently, algorithm performance improves." Year=1997} @Article{pastra2008, Author="{Pastra, Katerina}", Title="{COSMOROE: A cross-media relations framework for modelling multimedia dialectics}", Journal="Multimedia Systems", Volume=14, Number=5, Pages="299-323", Note="Citation of Taboada and Mann 2006, part 1", Abstract="Though everyday interaction is predominantly multimodal, a purpose-developed framework for describing the semantic interplay between verbal and non-verbal communication is still lacking. This lack not only indicates one's poor understanding of multimodal human behaviour, but also weakens any attempt to model such behaviour computationally. In this article, we present COSMOROE, a corpus-based framework for describing semantic interrelations between images, language and body movements. We argue that in viewing such relations from a message-formation perspective rather than a communicative goal one, one may develop a framework with descriptive power and computational applicability. We test COSMOROE for compliance to these criteria, by using it for annotating a corpus of TV travel programmes; we present all particulars of the annotation process and conclude with a discussion on the usability and scope of such annotated corpora." Year=2008} @Article{patry92, Author="{Patry, R.}", Title="{The Problem of Cohesive Force - Is It a Question of Distance or of Function}", Journal="Linguistique", Volume=28, Number=2, Pages="17-33", Year=1992} @InCollection{pelsmaekers-etal98, Author="{Pelsmaekers, Katja and Braecke, Chris and Geluykens, Ronald}", Title="{Rhetorical relations and subordination in L2 writing}", BookTitle="Linguistic Choice across Genres: Variation in Spoken and Written English", Editor="Sánchez-Macarro, Antonia and Carter, Ronald", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="191-213", Year=1998} Author="{Peng, Gracie}", Title="{Using Rhetorical Structure Theory (RST) to describe the development of coherence in interpreting trainees}", Journal="Interpreting", Volume=11, Number=2, Pages="216-243", Note="Citation of: Taboada, dissertation; RST web site", Year=2009} @TechReport{penn-treebank2003, Author="{Penn Discourse Treebank}", Title="{Annotation Guidelines for the Penn Discourse TreeBank}", Institution="University of Pennsylvania, Institure for Research in Cognitive Science", Note="Downloads as postscript. Also available as a webpage http://www.cis.upenn.edu/~dltag/annotation-manual/annotation-manual.html", Type="Manual", Abstract="Annotation manual for DLTAG, including instructions for using the annotation tool." Year=2003} @Article{perfetti97, Author="{Perfetti, C. A.}", Title="{Sentences, individual differences, and multiple texts: Three issues in text comprehension}", Journal="Discourse Processes", Volume=23, Number=3, Pages="337-355", Abstract="Three mini-essays review the progress made on two traditional problems and one newer problem in discourse understanding. The first traditional problem is the relationship between individual sentences and discourses. The role of discourse factors on sentence comprehension has received continuing attention, whereas the complementary question of sentences' contribution to discourse comprehension has been neglected. Recent work may have redressed this neglect to some extent. The second traditional topic is individual differences in discourse comprehension; the conclusion is that there has been substantial refinement of earlier hypotheses about the basic word and functional memory sources of such differences, whereas research on higher level causal factors remains inconclusive. The newer third problem, the representation of multiple texts, exposes fresh views of problems of discourse, especially the contrast between situation and text models. A recent representational Documents Model is briefly described. The conclusion suggests some unifying threads among these three problems." Year=1997} @InProceedings{pery-woodley98, Author="{Péry-Woodley, Marie-Paule}", Title="{Signalling in written text: A corpus-based approach}", Booktitle="Proceedings of COLING-ACL Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="79-85", Year=1998} @Article{pery-woodley, Author="{Péry-Woodley, Marie-Paule}", Title="{Modes d'organisation et de signalisation dans des textes procéduraux}", Journal="Langages", Volume=141, Pages="28-46", Abstract="Presents an analysis of instructional text, noting that there are more ways of signalling structure than just by lexical marking (i.e. layout and punctuation). RST trees are provided along with the texts." Year=2001} @TechReport{pianta-not97, Author="{Pianta, Emanuele and Not, Elena}", Title="{A Modular Text Planning Architecture for a Multilingual Setting}", Institution="ITC-IRST", Note="PDF is backwards." Number="Ref. No. 9701-06", Abstract="Presents the solution adopted in the GIST multilingual generation system, based on a distinction between domain specific and general communication knowledge. Proposes a modular architecture, emphasizing the role of domain specific knowledge and we argue for the need for making this information available throughout the planning process. RST is the representation mode of choice for rhetorical structure. Seems to be a recap of (Not Pianta 1995)", Year=1997} @Article{pineda-garza2000, Author="{Pineda, L. and Garza, G.}", Title="{A model for multimodal reference resolution}", Journal="Computational Linguistics", Volume=26, Number=2, Pages="139-193", Abstract="An important aspect of the interpretation of multimodal messages is the ability to identify when the same object in the world is the referent of symbols in different modalities. To understand the caption of a picture, for instance, one needs to identify the graphical symbols that are referred to by names and pronouns in the natural language text. One way to think of this problem is in terms oft he notion of anaphora; however, unlike linguistic anaphoric inference, in which antecedents for pronouns are selected from a linguistic context, in the interpretation of the textual part of multimodal messages the antecedents ave selected from a graphical context. Under this view, resolving multimodal references is like resolving anaphora across modalities. Another way to see the same problem is to look at pronouns in texts about drawings as deictic. In this second view, the context of interpretation of a natural language term is defined asa set of expressions of a graphical language with well-defined syntax and semantics. Natural language and graphical terms are thought of as standing in a relation of translation similar to the translation relation that holds between natural languages. In this paper a theory based on this second view is presented. In this theory, the relations between multimodal representation and spatial deixis, on the one hand, and multimodal reasoning and deictic inference, on the other, are discussed. An integrated model of anaphoric and deictic resolution in the context of the interpretation of multimodal discourse is also advanced." Year=2000} @InProceedings{pisanski2006, Author="{Pisanski Peterlin, Agnes}", Title="{Iskanje pragmaticnih enot v neoznacenem korpusu: primer kažipotov}", Booktitle="Proceedings of the Fifth Slovenian and First International Language Technologies Conference", Address="Ljubljana, Slovenia", Year=2006} @Book{pit2003, Author="{Pit, Mirna}", Title="How to Express Yourself with a Causal Connective: Subjectivity and Causal Connectives in Dutch, German and French", Publisher="Rodopi", Address="Amsterdam", Year=2003} @TechReport{poesio-dieugenio-keohane20002, Author="{Poesio, Massimo and Di Eugenio, Barbara and Keohane, Gerard}", Title="{Discourse Structure and Anaphora: An Empirical Study}", Institution="University of Essex", Number="TN-02-02", Type="NLE Technical Note", Year=2002} @Article{poesio-etal2006, Author="{Poesio, Massimo and Patel, Amrita and Di Eugenio, Barbara}", Title="{Discourse structure and anaphora in tutorial dialogues: An empirical analysis of two theories of global focus}", Journal="Research on Language and Computation", Volume=4, Pages="229-257", Year=2006} @Article{polanyi88, Author="{Polanyi, Livia}", Title="{A formal model of the structure of discourse}", Journal="Journal of Pragmatics", Volume=12, Pages="601-638", Abstract="Describes the Linguistic Discourse Model consisting of a set of discourse rules, specifying possible discourse constituents; a set of recursive rules of discourse formation, specifiying how constituents relate to one another; and a set of semantic interpretation rules, which assign a semantic and pragmatic interpretation to each clause, and to the discourse as a whole. Graphically, LDM results in a Discourse Parse Tree, capturing structural and semantic relations." Year=1988} @TechReport{polanyi96, Author="{Polanyi, Livia}", Title="{The Linguistic Structure of Discourse}", Institution="CSLI", Number="CSLI-96-200", Type="Technical Report", Year=1996} @InCollection{polanyi2001, Author="{Polanyi, Livia}", Title="{The linguistic structure of discourse}", BookTitle="The Handbook of Discourse Analysis", Editor="Schiffrin, Deborah and Tannen, Deborah and Hamilton, Heidi E." Publisher="Blackwell", Address="Malden, Mass", Pages="265-281", Year=2001} @InProceedings{polanyi-etal2004, Author="{Polanyi, Livia and Culy, Christopher and van der Berg, Martin and Thione, Gian Lorenzo and Ahn, David}", Title="{A rule based approach to discourse parsing}", Booktitle="Proceedings of the 5th SIGdial Workshop in Discourse and Dialogue", Address="Cambridge, MA", Pages="108-117", Year=2004} @InProceedings{polanyi-etal-acl2004, Author="{Polanyi, Livia and Culy, Christopher and van der Berg, Martin and Thione, Gian Lorenzo and Ahn, David}", Title="{Sentential structure and discourse parsing}", Booktitle="Proceedings of the ACL 2004 Workshop on Discourse Annotation", Address="Barcelona, Spain", Year=2004} @Article{polanyi-scha83, Author="{Polanyi, Livia and Scha, R. J. H.}", Title="{The syntax of discourse}", Journal="Text", Volume=3, Number=3, Pages="261-270", Abstract="Presents a model of discourse syntactic structure in which each clause is a minimal discourse unit, and the grammar is specified in terms of a recursive transition network. Discourse markers signal Push and Pop moves into and out of embedded discourse units." Year=1983} @InProceedings{polanyi-vandenBerg99, Author="{Polanyi, Livia and van den Berg, Martin}", Title="{Logical structure and discourse anaphora resolution}", Booktitle="Proceedings of the Workshop on the Relation of Discourse/Dialogue Structure and Reference in the 37th Annual Meeting of the Association for Computational Linguistics (ACL-99)", Address="College Park, Maryland", Pages="110-118", Year=1999} @PhDThesis{potter2007, Author="Potter, Andrew", Title="{An Investigation of Interactional Coherence in Asynchronous Learning Environments}", School="Nova Southeastern University", Note="Citation of: book, Text Technology paper, Mann & Taboada (both), web site", Type="Ph.D. dissertation", Abstract="Numerous studies have affirmed the value of asynchronous online communication as a learning resource. Several investigations, however, have indicated that discussions in asynchronous environments are often neither interactive nor coherent. This research sought to develop an enhanced understanding of interactional coherence in asynchronous learning environments. The study used Rhetorical Structure Theory (RST) to analyze and assess the coherence of a several asynchronous discussions. The analysis revealed that the discussions were structurally dynamic. While RST structures resulting from static documents are acyclic tree-shaped structures, the rhetorical networks representing asynchronous threads are frequently cyclic. Thus, the analysis required a modified form of RST based on reduced constraints and restricted schemas. By this means, it was possible to create structural models of the discussions. These models were used to investigate asynchronous argumentation and topic drift and to perform a comparative analysis of multiple discussions. The investigation found argumentation was more prevalent in some groups than others. In one group the analysis indicated the dominant mode of interaction was disagreement; in another group, argumentation was generally constructive; and in a third group, argumentation tended to be supportive and concessive. The investigation found that topic drift does not occur as a matter of chance. Participants use topic drift in order to adapt discussion to a topic of preference. As such, topics do not drift so much as they are pushed and pulled. A consequence of this process is that threads often begin with a strong research-based opening message, but descend to anecdotes and personal commentary. The conferencing systems used for the discussions were similar in their features, but the discussions differed, particularly in their use of threading. In one group, less than half of the messages were threaded, with the remainder posted as singletons. In other groups most of the messages were in threads. This research provides a framework and a terminology for fine-grained analysis of interactional coherence. By showing the applicability of RST to asynchronous discussion, the study has offered evidence that assessment technology could be developed for online discussions. In addition, the development of rhetorical networks as a directed graph theory for representing the semantics of asynchronous interaction could lead to new knowledge representation technologies for multi-agent collaboration systems." Year=2007} @InCollection{potter-aaai2007, Author="{Potter, Andrew}", Title="{A discourse approach to explanation aware knowledge representation}", BookTitle="Explanation-Aware Computing: Papers from the 2007 AAAI Workshop", Editor="Roth-Berghofer, T. and Schulz, S. and Leake, D. B. and Bahls, D", Publisher="AAAI Press", Address="Menlo Park, CA", Pages="56-63", Abstract="This study describes a discourse approach to explanation aware knowledge representation. It presents a reasoning model that adheres to argumentation as found in written discourse, intended for use in intelligent human-computer collaboration and inter-agent deliberation. The approach integrates the Toulmin model with Rhetorical Structure Theory and Perelman and Olbrechts-Tyteca's (1958) strategic forms of argumentative processes to define a set of constraints for governing argumentative interactions and formulating explanations in an ontologically normalized manner. Arguments, when satisfied, are instantiated into a dynamic rhetorical network that represents the system's model of the situation. Two modalities of instantiation are proposed. Inferential instantiation is used when a claim may be inferred from a ground, and synthetic instantiation is used for descriptive argumentation where both ground and claim must be satisfied for the argument to be instantiated. The instantiation process maps arguments into the network using interaction links. Defined interactions include accrual, concomitance, backing, substantiation, dissociation, rebuttal, undercut, and confusion. It is envisioned that communities of agents endowed with reasoning capabilities would engage in collaborative explanatory argumentation, using these interactions as mechanisms for detecting and managing conflict and agreement." Year=2007} @InProceedings{potter-ecai2008, Author="{Potter, Andrew}", Title="{Linked and convergent structures in discourse-based reasoning}", Booktitle="ECAI 2008 Workshop on Explanation Aware Computing (ExaCt 2008)", Address="Patras, Greece", Year=2008} @Article{potter-internet2008, Author="{Potter, Andrew}", Title="{Interactional coherence in asynchronous learning networks: A rhetorical approach}", Journal="The Internet and Higher Education", Volume=11, Number=2, Pages="87-97", Note="Citation of: Taboada and Mann (both parts), dissertation", Abstract="Numerous studies have affirmed the value of asynchronous online communication as a learning resource. Several investigations, however, have indicated that discussions in asynchronous environments are often neither interactive nor coherent. The research reported sought to develop an enhanced understanding of interactional coherence, argumentation, and topic drift in asynchronous learning environments. Rhetorical structure theory (RST) was used to analyze and assess the coherence of several asynchronous discussions. Findings include that asynchronous discussions take the form of dynamic rhetorical structures which are continuously redefined as new messages are added to a thread, that argumentation may be more prevalent in some discussions than others, that topic drift does not seem to occur as a matter of chance, but rather topics are manipulated to suit the individual preferences of the participants, and that the use of threading differs considerably from one discussion group to another. By demonstrating the applicability of RST, argumentative analysis, and topic drift analysis to asynchronous discussion, this research provides a framework and a terminology for fine-grained analysis of interactional coherence. By showing the applicability of RST to asynchronous discussion, this study has offered evidence that essay assessment technology could be developed for evaluating the quality of online discussions. The development of rhetorical networks as a graph theory for representing the semantics of asynchronous interaction could lead to a richer knowledge representation technology for inter-agent collaboration." Year=2008} @Article{potter-ki2008, Author="{Potter, Andrew}", Title="{Generating discourse-based explanations}", Journal="Künstliche Intelligenz", Volume=22, Number=2, Pages="28-31", Abstract="Humans and artificial agents need to be able to explain themselves to one another. They need to be able to present their perspectives and assess the views of others. This paper describes an approach to explanation aware reasoning, using underlying structures of natural discourse and argumentation theory. By positioning argumentation, explanation, and defeasibility concepts as first-class ontological entities, we can create an explanation-aware solution for multi-agent environments. Arguments are linked using ontologically specified interactions, such as substantiation, rebuttal, and accrual. It is envisioned that communities of human and artificial agents will engage in collaborative explanatory argumentation using argumentative structures and interactions for discovering knowledge and managing and navigating conflict and agreement." Year=2008} @TechReport{power-etal99, Author="{Power, Richard and Doran, Christine and Scott, Donia}", Title="{Generating Embedded Discourse Markers from Rhetorical Structure}", Institution="University of Brighton, Information Technology Research Institute", Note="Also appears in proceedings of EWNLG 7", Number="ITRI-99-15", Type="Technical Report", Abstract="Presents a system for generating text with multiple embedded discourse relations, all of which are lexically marked. Factors influencing the cue choice include syntactic information, RST, notions of text-grammar and findings from psycholinguistic research. The end result is a unified feature-based account." Year=1999} @Article{power-etal2003, Author="{Power, Richard and Scott, Donia and Bouayad-Agha, Nadjet}", Title="{Document structure}", Journal="Computational Linguistics", Volume=29, Number=2, Pages="211-260", Year=2003} @Article{prasad-etal2006, Author="{Prasad, Rashmi and Dinesh, Nikhil and Lee, Alan and Joshi, Aravind K and Webber, Bonnie}", Title="{Attribution and its annotation in the Penn Discourse TreeBank}", Journal="Traitement Automatique des Langues", Volume=47, Number=2, Pages="43-63", Abstract="In this paper, we describe an annotation scheme for the attribution of abstract objects (propositions, facts, and eventualities) associated with discourse relations and their arguments annotated in the Penn Discourse TreeBank. The scheme aims to capture both the source and degrees of factuality of the abstract objects through the annotation of text spans signalling the attribution, and of features recording the source, type, scopal polarity, and determinacy of attribution." Year=2006} @InProceedings{pdtb2008, Author="{Prasad, Rashmi and Lee, Alan and Dinesh, Nikhil and Miltsakaki, Eleni and Campion, Geraud and Joshi, Aravind K. and Webber, Bonnie}", Title="Penn Discourse Treebank Version 2.0, LDC2008T05", Publisher="Linguistic Data Consortium", Number=LDC2008T05, Year=2008} @PhDThesis{prevot2004, Author="Prévot, Laurent", Title="{Structures sémantiques et pragmatiques pour la modélisation de la cohérence dans des dialogues finalisés}", School="Université Paul Sabatier", Note="Citation of: 2001 PhD thesis", Type="PhD dissertation", Year=2004} @Article{prevot-etal2009, Author="{Prévot, Laurent and Vieu, Laure and Asher, Nicholas}", Title="{Une formalisation plus précise pour une annotation moins confuse: la relation d'Élaboration d'entité}", Journal="Journal of French Language Studies", Volume=19, Number=2, Pages="207-228", Year=2009} @Article{prust-etal94, Author="{Prust, H. and Scha, R. and Vandenberg, M.}", Title="{Discourse grammar and verb phrase anaphora}", Journal="Linguistics and Philosophy", Volume=17, Number=3, Pages="261-327", Year=1994} @Article{rada-etal93, Author="{Rada, R. and Wang, W. G. and Birchall, A.}", Title="{Retrieval hierarchies in hypertext}", Journal="Information Processing and Management", Volume=29, Number=3, Pages="359-371", Abstract="We have developed a collaborative, reuse hypertext system that has novel browsing and retrieval characteristics. The system, called Many Using and Creating Hypertext (MUCH), has been implemented on a network of UNIX workstations and used extensively in our group. This paper presents the model underlying the use of the MUCH system with respect to organizing, retrieving, and reorganizing information. In order to reuse information successfully, one must first organize it, then retrieve it, and finally reorganize it. The storage layer of hypermedia is logically based on nodes and links, and the MUCH system assumes that the names for these nodes and links represent a kind of semantic net. Documents, thesauri, and discussions may all be connected in this semantic net. The various functionalities of the system then exploit the knowledge in this semantic net. Traversals of the net with various filters are the basis for the views that users get of the semantic net. The standard perspective is of a fold-unfold outline that represents a fisheye view of the semantic net. The reorganization of information also depends on a selection of nodes and their presentation within a connected subnet." Year=1993} @InProceedings{radev2000, Author="{Radev, Dragomir}", Title="{A common theory of information fusion from multiple text sources. Step one: Cross document structure}", Booktitle="Proceedings of 1st SIGdial Workshop on Discourse and Dialogue", Address="Hong Kong", Pages="74-83", Year=2000} @Article{radev-etal-centroid2004, Author="{Radev, Dragomir and Jing, Hongyan and Stys, Malgorzata and Tam, Daniel}", Title="{Centroid-based summarization of multiple documents}", Journal="Information Processing and Management", Volume=40, Pages="919-938", Abstract="We present a multi-document summarizer, MEAD, which generates summaries using cluster centroids produced by a topic detection and tracking system. We describe two new techniques, a centroid-based summarizer, and an evaluation scheme based on sentence utility and subsumption. We have applied this evaluation to both single and multiple document summaries. Finally, we describe two user studies that test our models of multi-document summarization." Year=2004} @InProceedings{radev-etal2004, Author="{Radev, Dragomir and Otterbacher, Jahna and Zhang, Zhu}", Title="{CST Bank: A corpus for the study of cross-document structural relationships}", Booktitle="Proceedings of 4th International Conference on Language Resources and Evaluation, LREC", Address="Lisbon, Portugal", Year=2004} @InProceedings{rambow90, Author="{Rambow, Owen}", Title="{Domain communication knowledge}", Booktitle="Proceedings of 5th International Workshop on Natural Language Generation", Address="Dawson, Pennsylvania", Pages="87-94", Year=1990} @InProceedings{rambow93, Author="{Rambow, Owen}", Title="{Rhetoric as knowledge}", Booktitle="Proceedings of ACL Workshop on Intentionality and Structure in Discourse Relations", Address="Columbus, Ohio", Pages="102-105", Year=1993} @Book{rambow93, Editor="{Rambow, Owen}", Title="Proceedings of the ACL Workshop on Intentionality and Structure in Discourse Relations", Publisher="ACL", Address="Columbus, Ohio", Year=1993} @Article{ramsay2000, Author="{Ramsay, Guy}", Title="{Linearity in rhetorical organisation: A comparative cross-cultural analysis of newstext from the People's Republic of China and Australia}", Journal="International Journal of Applied Linguistics", Volume=10, Number=2, Pages="241-258", Abstract="Addresses comprehension issues faced by L2 learners of Modern Standard Chinese through a comparative study of the RST structures of two lengthy Australian and Chinese news journal texts. The small corpus admittedly limits the generality of the findings, but do give some indications of what could be going on. Pedagogical implications for the L2 classroom are also addressed." Year=2000} @Article{ramsay2001, Author="{Ramsay, Guy}", Title="{What are they getting at? Placement of important ideas in Chinese newstext: A contrastive analysis with Australian newstext}", Journal="Australian Review of Applied Linguistics", Volume=24, Number=2, Pages="17-34", Abstract="Presents a contrastive analysis of Chinese and Australian newstexts, comparing the rhetorical structures using RST. There is a discussion of the pedagogical implications of the contrasts found for L2 learners of Chinese." Year=2001} @Article{ramsay-ejournal2001, Author="{Ramsay, Guy}", Title="{Rhetorical styles and newstexts: A contrastive analysis of rhetorical relations in Chinese and Australian news-journal text}", Journal="E-Journal of Asian Linguistics and Language Teaching", Volume=1, Number=1, Abstract="To date, contrastive rhetoric studies have produced equivocal evidence of variation in rhetorical styles across Chinese and English language discourse, as based on the prevailing 'direct' versus 'indirect' dichotomy. Resolving the issue of rhetorical difference is of particular importance to the teaching of Modern Standard Chinese, since awareness of any such variation is crucial to the development of communicative competence in language learners. In order to contribute to and extend continuing debate, this study employs Rhetorical Structure Theory to analyse rhetorical relations present in Chinese and Australian news-journal text. Results demonstrate considerably less emphasis on backing-up and corroborating claims (evidence relations), and on debates and contentions (opposition, concession and contrast relations) in the Chinese newstexts. This may prove problematic for Australian readers. The relevance of analyses of this type to the classroom is discussed." Year=2001} @Article{rebeyrolle-etal2009, Author="{Rebeyrolle, Josette and Jacques, Marie-Paule and Péry-Woodley, Marie-Paule}", Title="{Titres et intertitres dans l'organisation du discours}", Journal="Journal of French Language Studies", Volume=39, Number=2, Pages="269-290", Note="Citation of: Taboada and Mann 2006, part 1", Year=2009} @Article{redeker91, Author="{Redeker, Gisela}", Title="{Review article: Linguistic markers of linguistic structure}", Journal="Linguistics", Volume=29, Number=6, Pages="1139-1172", Year=1991} @InCollection{redeker-inpress, Author="{Redeker, Gisela}", Title="{Coherence and structure in text and discourse}", BookTitle="Abduction, Belief, and Context in Dialogue. Studies in Computational Pragmatics", Editor="Black, William and Bunt, Harry", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="233-263", Abstract="Presents a theory of discourse coherence that is well-adapted to either monologue or dialogue. Two corpus studies are also shown, supporting the argument that coherence should be thought of as consisting of three parallel components: ideational (semantic) structure, rhetorical structure, and sequential (segment) structure." Year=2000} @InCollection{redeker2006, Author="{Redeker, Gisela}", Title="{Discourse markers as attentional cues at discourse transitions}", BookTitle="Approaches to Discourse Particles", Editor="Fischer, Kerstin", Publisher="Elsevier", Address="Amsterdam", Pages="339-358", Year=2006} @InProceedings{redeker-egg-attribution2006, Author="{Redeker, Gisela and Egg, Markus}", Title="{Says who? On the treatment of speech attributions in discourse structure}", Booktitle="Proceedings of the Workshop “Constraints in Discourse”", Address="Maynooth University, Ireland", Pages="140-146", Year=2006} @InProceedings{reed-daskalopolu98, Author="{Reed, Chris and Daskalopolu, Aspassia}", Title="{Modelling contractual arguments}", Booktitle="4th International Conference on Argumentation", Address="Amsterdam, Netherlands", Pages="686-692", Year=1998} @InProceedings{reed-long97, Author="{Reed, Chris and Long, Derek}", Title="{Persuasive dialogue}", BookTitle="OSSA Conference on Argument and Rhetoric", Address="St. Catherine's, Canada", Abstract="Argues for a study of monologue as a turn in dialogue, putting forward an account which examines the argumentation involved in persuasive monologue, drawing upon commitment-based theories of dialogue. The various differences between monologue and dialogue are discussed, with particular reference to the possibility of designing a monologue game in which commitments are dynamically incurred and updated as the monologue is created. There is also discussion of why such an approach is preferable to RST and other computationally-based approaches." Year=1997} @InProceedings{reed-long97b, Author="{Reed, Chris and Long, Derek}", Title="{Multiple subarguments in logic, argumentation, rhetoric and text generation}", Booktitle="Proceedings of International Joint Conference on Quantitative and Qualitative Practical Reasoning", Publisher="Springer", Address="Bad Honnef, Germany", Pages="496-510", Year=1997} @TechReport{reed-long97c, Author="{Reed, Chris and Long, Derek}", Title="{Generating Punctuation in Written Documents}", Institution="Department of Computer Science, University College", Number="RN/97/157", Type="Technical Report", Abstract="A framework for the generation of natural language argument is summarized, and is then shown to be suited to the generation of a number of forms of punctuation which have not be adequately accounted for. It is shown that formatting such as paragraph breaks, footnotes, and quotations require an abstract, intention based representation." Year=1997} @InProceedings{reed-long98, Author="{Reed, Chris and Long, Derek}", Title="{Generating the structure of argument}", Booktitle="Proceedings of 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (COLING-ACL'98)", Address="Montréal, Canada", Pages="1091-1097", Year=1998} @InProceedings{reitter2002, Author="{Reitter, David}", Title="Rhetorical Theory in LaTeX with the RST Package", Pages="7", Abstract="A Technical manual for the generation of RST trees in LaTeX." Year=2002} @InProceedings{reitter2003b, Author="{Reitter, David}", Title="{Simple signals for complex rhetorics: On rhetorical analysis with rich-feature support vector models}", Booktitle="Sprachthechnologie für die multilinguale Kommunikation", Address="Sankt Augustin, Germany", Year=2003} @PhDThesis{reitter2003, Author="Reitter, David", Title="{Rhetorical Analysis with Rich Feature Support Vector Models}", School="University of Potsdam", Type="Master's thesis", Abstract="Discusses an approach to the automated recognition of discourse relations using a machine learning approach trained on German and English corpora. Also covers the annotation scheme incorporating underspecification." Year=2003} @Article{reitter-journal2003, Author="{Reitter, David}", Title="{Simple signals for complex rhetorics: On rhetorical analysis with rich-feature support vector models}", Journal="LDV-Forum, Journal for Computational Linguistics and Language Technology", Volume=18, Number=1-2, Pages="38-52", Year=2003} @InProceedings{reitter-stede2003, Author="{Reitter, David and Stede, Manfred}", Title="{Step by step: Underspecified markup in incremental rhetorical analysis}", Booktitle="Proceedings of EACL 4th International Workshop on Interpreted Corpora", Address="Budapest, Hungary", Year=2003} @Article{renkema2006, Author="{Renkema, Jan}", Title="{How to proceed with ambiguity in discourse relations? A proposal based on connectivity variables}", Journal="Studies in Communication Sciences", Volume=6, Number=1, Pages="117-134", Note="Citation of: book, Taboada and Mann (both papers)", Year=2006} @Article{renkema2008, Author="{Renkema, Jan}", Title="{Relaciones discursivas y variables de conectividad}", Journal="Revista Signos", Volume=41, Number=66, Pages="65-80", Note="Citation of: book, Taboada and Mann (parts 1 and 2)", Year=2008} @Book{renkema2009, Author="{Renkema, Jan}", Title="The Texture of Discourse", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Note="Citation of: 1. Pragmatics 2006 paper (turn-taking) 2. Taboada and Mann 2006 part 1 3. Taboada and Mann 2006 part 2 4. Taboada 2004 book 5. Taboada and Renkema, corpus", Year=2009} @PhDThesis{rienks2007, Author="Rienks, Rutger", Title="{Meetings in Smart Environments: Implications of Progressing Technology}", School="University of Twente", Note="Citation of Murray et al; Taboada and Mann ('Looking back..')", Type="Ph.D. dissertation", Year=2007} @InProceedings{rino-etal-comparison2004, Author="{Rino, Lucia Helena Machado and Pardo, Thiago Alexandre Salgueiro and Silla, Carlos Nascimento and Kaestner, Celso Antonio Alves and Pombo, Michael}", Title="{A comparison of automatic summarization systems for Brazilian Portuguese texts}", Booktitle="Proceedings of the XVII Brazilian Symposium on Artificial Intelligence (SBIA 2004)", Address="São Luís, Maranhão, Brazil", Year=2004} @TechReport{rino-scott96, Author="{Rino, Lucia Helena Machado and Scott, Donia}", Title="{A Discourse Model for Gist Preservation}", Institution="University of Brighton, Information Technology Research Institute", Number="ITRI-96-12", Type="Technical Report", Abstract="This paper describes an approach to gist preservation during automatic summarization whereby the source is a complex information structure which must be "pruned" and organized in such a way as to make it appropriate for textual expression. Uses the tri-level approach to discourse modelling (intentionality, coherence, semantics) to obtain summary message sources that highlight the central proposition of the discourse." Year=1996} @Article{risselada-spooren98, Author="{Risselada, Rodie and Spooren, Wilbert}", Title="{Introduction: Discourse markers and coherence relations}", Journal="Journal of Pragmatics", Volume=30, Pages="131-133", Note="Need Elsevier access via SFU library EJournals (needs login)", Abstract="Introduction to the special issue on discourse markers and relations, 1998. Gives a nice "state of the union" on the field, as well as an inrtoduction to the articles contained within." Year=1998} @Article{rittgen2008, Author="{Rittgen, P.}", Title="{A contract-based architecture for business networks}", Journal="International Journal of Electronic Commerce", Volume=12, Number=4, Pages="115-145", Note="Cited References: *AMICE, 1993, CIMOSA OP SYST ARCH AALST WMP, 2003, DISTRIBUTED PARALLEL, V14, P5 AALST WMP, 2005, INFORM SYST, V30, P245 ADELBERG B, 1998, P ACM SIGMOD INT C M, P283 ALCHIAN AA, 1972, AM ECON REV, V62, P777 ARTYSHCHEV S, 2005, INTEROPERABILITY ENT, P173 AUSTIN JL, 1962, DO THINGS WORDS BAECKER RM, 1993, READINGS GROUPWARE C BARKER R, 1990, CASE METHOD ENTITY R BENNET S, 1999, OBJECT ORIENTED SYST BERNAUER M, 2003, P 7 WORLD MULT SYST, P30 BERNUS P, 1996, COMPUT INTEGR MANUF, V9, P179 CHANDRA C, 2000, P 2 INT C SIM GAM TR, P345 CLEMONS EK, 1993, J MANAGEMENT INFORMA, V10, P9 COASE RH, 1937, ECONOMICA, V4, P386 DEAN DL, 2000, GROUP DECIS NEGOT, V9, P109 DEMOOR A, 2004, INT NEGOTIATION, V9, P31 DENNING PJ, 1995, INTERFACES, V25, P42 DIETZ JLG, 1999, P 18 INT C CONC MOD, P188 DIETZ JLG, 2004, P OTM CONF INT C COO, P85 ERICSSON K, 1993, PROTOCOL ANAL VERBAL FIELDING NG, 1998, COMPUTER ANAL QUALIT FOX G, 1995, P 28 ANN HAW INT C S, P485 FREDERIKS RJM, 2006, DATA KNOWL ENG, V58, P4, DOI 10.1016/j.datak.2005.05.007 GIAGLIS G, 1996, P 1996 WINT SIM C SA, P1297 GIAGLIS GM, 1997, INFORMATICA, V21, P613 GIAGLIS GM, 1999, INT J INFORM MANAGE, V19, P219 GOLDKUHL G, 1993, HUMAN ORG SOCIAL DIM, P107 GOLDKUHL G, 1996, COMMUNICATION MODELI, P1 GOLDKUHL G, 2004, P 12 EUR C INF SYST GROSOF BN, 1999, P 1 ACM C EL COMM EC, P68 GURBAXANI V, 1991, COMMUN ACM, V34, P59 HABERMAS J, 1984, THEORY COMMUNICATIVE, V1 HLUPIC V, 1998, P 1998 WINT SIM C, P1363 HOLLAND CP, 1997, ORGAN SCI, V8, P475 HOPPENBROUWERS SJB, 2005, P 10 INT WORK C LANG, P139 HOPPENBROUWERS SJB, 2006, SEBGIS P 2, V4278, P1242 INTRONA LD, 1997, LOGISTICS INFORMATIO, V10, P235 JENSEN MC, 1976, J FINANC ECON, V3, P305 KARLAPALEM K, 2001, P INT C CONC MOD ER2, P193 KELLER F, 2003, 10 IEEE S WORKSH ENG KERSTEN GE, 2004, E COMMERCE WEB TECHN, P106 KLEIN B, 1978, J LAW ECON, V21, P297 KOHNE F, 2005, P 12 RES S EM EL MAR, P19 KRISHNA PR, 2005, INFORM TECHNOLOGY MA, V6, P363 LEHTINEN E, 1986, INFORM SYST, V11, P299 LIU KC, 2003, KNOWL-BASED SYST, V16, P101 MALONE TW, 1987, COMMUN ACM, V30, P484 MANN W, 1993, TEXT DESCRIPTION DIV, P39 MANN WC, 1988, TEXT, V8, P243 MEDINAMORA R, 1992, P C COMP SUPP COOP W, P281 MENZEL C, 1998, HDB ARCHITECTURES IN, P209 MILOSEVIC Z, 2004, P IFIP 18 WORLD COMP, P413 MOLINAJIMENEZ C, 2003, P IEEE INT C E COMM, P103 MORRIS WT, 1967, MANAGE SCI, V13, B707 ODONNELL M, 2000, P INT NAT LANG GEN C, P253 OULD M, 2005, BUSINESS PROCESS MAN PAUL RJ, 1999, AM BEHAV SCI, V42, P1551 PAUL RJ, 2003, P 2003 WINT SIM C, P1787 PAUL RJ, 2004, P 37 ANN HAW INT C S PERSSON A, 2001, ENTERPRISE MODELLING RITTGEN P, 2005, INFOCOMP J, V4, P23 RITTGEN P, 2006, EUR J INFORM SYST, V15, P70, DOI 10.1057/palgrave.ejis.300597 ROBOAM M, 1989, COMPUT INTEGR MANUF, V2, P82 ROSS S, 1973, AM ECON REV, V63, P134 ROUACHED M, 2005, LECT NOTES COMPUT SC, V3649, P410 SCHEER AW, 1999, ARIS BUSINESS PROCES SCHOOP M, 2001, COMPUT NETW, V37, P153 SCHOOP M, 2003, DATA KNOWL ENG, V47, P371, DOI 10.1016/S0169-023X(03)00065-X SEARLE JR, 1969, SPEECH ACTS ESSAY PH SHEN MX, 2001, LECT NOTES COMPUT SC, V2113, P274 SRINIVASAN A, 1995, MANAGE SCI, V41, P419 STAMPER R, 1991, INFORMATION SYSTEMS, P515 STROBEL M, 2001, ELECT COMMERCE RES J, V1, P335 VANBOMMEL P, 2006, LECT NOTES COMPUT SC, V4278, P1128 VANREIJSWOUD VE, 1996, THESIS DELFT U TECHN WEIGAND H, 2002, DECIS SUPPORT SYST, V33, P247 WEIGAND H, 2003, P 9 IFIP TC2 WG2 6 W, P3 WEYALAND JH, 2003, P 2003 WINT SIM C PI, P225 WILLEMAIN TR, 1994, OPER RES, V42, P213 WILLEMAIN TR, 1995, OPER RES, V43, P916 WILLIAMS TJ, 1994, COMPUT IND, V24, P141 WILLIAMSON OE, 1975, MARKETS HIERARCHIES WILLIAMSON OE, 1981, J ECON LIT, V19, P1537 WILLIAMSON OE, 1985, EC I CAPITALISM WILSON R, 1968, ECONOMETRICA, V36, P119 WINOGRAD T, 1986, UNDERSTANDING COMPUT Article", Abstract="Contracts coordinate the interactions between organizations in a business network. Conventional frame contracts often result in ambiguous agreements with operational details unspecified, making it hard to coordinate the network effectively and efficiently. This paper suggests a structured method for designing agreements and ensuring that their terms are observed in business transactions. Based on the assumption that governing a business network means managing the workflow between the member organizations, the contract consists primarily of process models at different levels of detail. A method is proposed for negotiating these models between the member organizations of the network and enacting them with the help of an interorganizational workflow system." Year=2008} @InProceedings{rocchi-zancanaro2003, Author="{Rocchi, Cesare and Zancanaro, Massimo}", Title="{Generation of video documentaries from discourse structures}", Booktitle="Proceedings of 9th European Workshop on Natural Language Generation (EWNLG 9)", Address="Budapest, Hungary", Year=2003} @Book{romera2004, Author="{Romera, Magdalena}", Title="Discourse Functional Units: The Expression of Coherence Relations in Spoken Spanish", Publisher="LINCOM", Address="Munich", Note="Citation of PhD dissertation", Year=2004} @InProceedings{rosner93, Author="{Rösner, Dietmar}", Title="{Intentions, rhetoric, or discourse relations? A case from multilingual document generation}", Booktitle="Proceedings of Workshop on Intentionality and Structure in Discourse Relations, ACL", Publisher="ACL", Address="Ohio State University", Pages="106-109", Year=1993} @InCollection{rosner-stede, Author="{Rösner, Dietmar and Stede, Manfred}", Title="{Customizing RST for the automatic production of technical manuals}", BookTitle="Aspects of Automated Language Generation", Editor="Dale, Robert and Hovy, Eduard and Rösner, Dietmar and Stock, Oliviero", Publisher="Springer", Address="Berlin", Pages="119-214", Abstract="Presents changes necessary to customize RST for the generation of instructional text. Specifically, this involves the creation of a number of new relations. Then, methodology is shown for converting RST trees to sentence plans." Year=1992} @Article{rossari2001, Author="{Rossari, Corinne}", Title="{Les relations de discours: Approches rhétoriques, approches pragmatiques et approches sémantiques}", Journal="Verbum", Volume=XXIII, Number=1, Pages="59-72", Year=2001} @InProceedings{rutledge-etal2000a, Author="{Rutledge, Lloyd and Bailey, Brian and van Ossenbruggen, Jacco and Hardman, Lynda and Geurts, Joost}", Title="{Generating presentation constraints from rhetorical structure}", Booktitle="Proceedings of 11th ACM conference on Hypertext and Hypermedia", Address="San Antonio, TX", Pages="19-28", Year=2000} @InProceedings{rutledge-etal2000b, Author="{Rutledge, Lloyd and Davis, Jim and van Ossenbruggen, Jacco and Hardman, Lynda}", Title="{Inter-dimensional hypermedia communicative devices for rhetorical structure}", Booktitle="Proceedings of International Conference on Multimedia Modeling (MMM00)", Address="Nagano, Japan", Pages="89-105", Year=2000} @InProceedings{sanfranj2007, Author="{Safranj, Jelisaveta}", Title="{Types of attribution relation in the Financial Times corpus}", Booktitle="Proceedings of English Language and Literature Studies: Structures across Cultures, ELLSSAC", Address="Belgrade", Year=2007} @InProceedings{sanfranj2008, Author="{Safranj, Jelisaveta}", Title="{Rhetorical organization of business English newspaper articles}", Booktitle="Proceedings of FLLAS International Conference: Language for Specific Purposes - Theory and Practice", Address="Belgrade", Year=2008} @PhDThesis{safranj-thesis2008, Author="Safranj, Jelisaveta", Title="{Rhetorical Structure in Business English Discourse}", School="University of Belgrade", Type="Ph.D. dissertation", Abstract="Rhetorical structure in business english discourse has been investigated on the corpus of 150 on-line business news articles published in The Financial Times newspaper. The scope of the study is on the distribution of rhetorical relations that hold between adjacent text spans and characterise journalistic genre on the whole and this particular type as well. Text analysis required building a discourse-tagged corpus in the framework of Rhetorical Structure Theory (Mann and Thompson, 1988) which addresses the notion of text coherence through text relations. The structure of analysed articles has been conventionally described by rhetorical relations that establish semantic and functional relations between adjacent text spans. This kind of approach explains coherence by postulating a hierarchical, connected structure of texts, in which every part of a text has a role, a function to play, with respect to other parts in the text. The analysis has proved that the articles are organised in the fashion of inverted pyramid, i.e. applying the principle of decreasing interest, which means that the facts are ranged according to their importance, not chronologically as they occured in certain situation, event or problem. A discourse-tagged corpus provided hierarchical discourse tree of every article. Further analysis showed the distribution of rhetorical relations through the segments of analyzed discourse tree and stated the most frequent relations in the corpus that characterize journalistic genre. Moreover, the structure of presented information in the articles have been described according to the distribution of relations through several segments of hierarchical discourse tree. The analysis carried out on document level describes the basic structure of business news articles by the means of rhetorical relations." Year=2008} @Article{salkie-oates99, Author="{Salkie, Raphael and Oates, Sarah Louise}", Title="{Contrast and Concession in French and English}", Journal="Languages in Contrast", Volume=2, Number=1, Pages="27-56", Abstract="The discourse markers but & although are similar but not identical in meaning. We investigate the relationship between them using data from the INTERSECT translation corpus. A collection of cases are examined where although corresponds to French mais. In order to explain the correspondences we draw on rhetorical structure theory (RST). By organizing RST relations in a hierarchy, & adding a new relation to the inventory of RST relations, we can give a systematic explanation of the relationship between contrast & concession. 2 Tables, 1 Figure, 2 Appendixes, 29 References. Adapted from the source document", Year=1999} @PhDThesis{sanders86, Author="Sanders, Ted", Title="{De invloed van globale teksteigenschappen op het begrijpen en onthouden van teksten (The influence of global properties of text on understanding and remembering text)}", School="Tilburg University", Type="master's thesis", Year=1986} @Article{sanders97, Author="{Sanders, Ted}", Title="{Semantic and pragmatic sources of coherence: On the categorization of coherence relations in context}", Journal="Discourse Processes", Volume=24, Pages="119-147", Abstract="Coherence Relations are broken down by the source of coherence, into two types: semantic (where the relation comes from the locutionary force) and pragmatic (where the relation comes from the illocutionary force). These are likened to the major split in relations proposed in (M&T 88). Using Paraphrases in an experiment to test readers' intuitions about the source of coherence led to favourable results. The expected paraphrases were generally selected according to the original predictions. A corpus study also indicates that there is some correspondence between text type and the presence of certain relations: pragmatic relations tend to surface in narrative styles, while semantic ones surface in simpler argumentative texts." Year=1997} @Article{sanders-etal2007, Author="{Sanders, Ted and Land, Jentine and Mulder, Gerben}", Title="{Linguistic markers of coherence improve text comprehension in functional contexts}", Journal="Information Design Journal", Volume=15, Number=3, Pages="219-235", Year=2007} @Article{sanders-noordman2000, Author="{Sanders, Ted and Noordman, Leo}", Title="{The role of coherence relations and their linguistic markers in text processing}", Journal="Discourse Processes", Volume=29, Number=1, Pages="37-60", Abstract="Focuses on the cognitive status of coherence relations. In psycholinguistic experiments, two aspects of relations were tested: what relation holds in the text sample, and how is it signalled? Explicit marking is shown to increase the speed of comprehension, but has no effect on recall. -- Need password access to Catchword for pdf! -- ABSTRACT FROM SOURCE: When readers process a text, they establish a coherent representation by means of coherence relations. This article focuses on the cognitive status of these relations. In an experiment using reading, verification, and free recall tasks, 2 crucial aspects of the structure of expository texts were investigated: the type of coherence relation between segments (problem-solution vs. list) and the linguistic marking of the relations by means of signaling phrases (implicit vs. explicit). Both factors affected text processing. Problem solution relations lead to faster processing, better verification, and superior recall. Explicit marking of the relations resulted in faster processing but did not affect recall. We conclude that the processing of a text segment depends on the relation it has with preceding segments. The relational marker has an effect during online processing, but its influence decreases over time. This contrasts with the effect of the coherence relation, which is also manifest in the recall." Year=2000} @InCollection{sanders-schilperoord2008, Author="{Sanders, Ted and Schilperoord, Joost}", Title="{Text structure as a window on the cognition of writing: How text analysis provides insights in writing products and writing processes}", BookTitle="Handbook of Writing Research", Editor="MacArthur, Charles A and Graham, Steve and Fitzgerald, Jill", Publisher="Guilford Press", Address="New York", Pages="386-402", Year=2008} @InCollection{sanders-spooren99, Author="{Sanders, Ted and Spooren, Wilbert}", Title="{Communicative intentions and coherence relations}", BookTitle="Coherence in Spoken and Written Discourse: How to Create It and How to Describe It", Editor="Bublitz, Wolfram and Lenk, Uta and Ventola, Eija", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="235-250", Abstract="Presents an argument for the need to represent ideational and interpersonal information, but that the notion of intentionality must be represented at a level other than discourse structure." Year=1999} @Article{sanders-etal92, Author="{Sanders, Ted and Spooren, Wilbert and Noordman, Leo}", Title="{Toward a taxonomy of coherence relations}", Journal="Discourse Processes", Volume=15, Number=1, Pages="1-35", Abstract="Presents a taxonomy of relations, along with a supporting experiment using text fragments. Further experiments involving connectives are said to indicate the cognitive salience of the primitives used in the taxonomy." Year=1992} @Article{sanders-etal93, Author="{Sanders, Ted and Spooren, Wilbert and Noordman, Leo}", Title="{Coherence relations in a cognitive theory of discourse representation}", Journal="Cognitive Linguistics", Volume=4, Number=2, Pages="93-133", Abstract="Once again presents the taxonomy of relations based on four primitives. Two psycholinguistic experiments are presented that test the validity of the taxonomy. The taxonomy is shown to be plausible, and the primitives are psychologically salient." Year=1993} @InProceedings{sanders-vanwijk93, Author="{Sanders, Ted and van Wijk, Carel}", Title="PISA A Procedure for Incremental Structure Analysis of Expository Texts", Abstract="Presents PISA, which is meant ot overcome the shortcomings of other theories (like RST): annotator disagreement and subjectivity. PISA is algorithmic, dependent only upon linguistic and lexical knowledge, and psychologically plausible. This last is attained through the use of relations which have been tested for psychological plausibility in separate research. Another abstract: Abstract Intuitions about text structures are formulated in ordered sets of production rules that constitute an analytic procedure so as to solve the indeterminacy for the domain of explanatory texts. Rhetorical structure theory, the linguistic discourse model, & the procedure for incremental structure analysis (PISA) are reviewed in both hierarchical & relational aspects. An illustration of the analytic procedure is in the form of a text of a male, aged 12, trying to explain the use of a telephone. The hierarchical structure of this text is provided, with its relational structure. Hierarchial & relational structures production is detailed, beginning with an overview that includes an inventory of the relevant segment features & a discussion of the input & output of PISA, & an explanation of some of its production rules & the hierarchical structures. Reasons for particular rules & text regularities are outlined, with attention to the structure of explanations, the linguistic markers of text structures, & the flexibility of the procedure. PISA is being used in several current research projects, & its applications for writing behavior, text quality, & procedural & intuitive analysis are considered. 3 Tables, 5 Figures, 1 Appendix, 81 References. Adapted from the source document", Year=1993} @Article{sanders-vanwijk96, Author="{Sanders, Ted and van Wijk, Carel}", Title="{PISA: A procedure for analyzing the structure of explanatory texts}", Journal="Text", Volume=16, Number=1, Pages="91-132", Year=1996} @Article{safranj2008, Author="{Sanfranj, Jelisaveta}", Title="{Retoricka struktura u diskursu engleskog poslovnog jezika}", Journal="Pedagoska stvarnost", Volume=54, Number=9-10, Pages="990-1003", Note="Citation of: JofPrags 2006", Year=2008} @Article{sarjala94, Author="{Sarjala, Marja}", Title="{Signalling of reason and cause relations in academic discourse}", Journal="Anglicana Turkuensia", Volume=13, Pages="89-98", Abstract="Discussion sections of psychological research articles in Finnish & English are inspected to compare the signaling of reason & cause relations. The framework is an assumption that semantic relations are universal & that rhetorical structure theory defines reason & cause as semantically close. An analysis based on Eugene O. Winter's (1977 [see abstract 8100590]) three categories of relation signaling (subordinators, conjuncts, & lexical signals) shows most reason & cause relations occur at clausal levels in Finnish & English, & English uses more explicit signaling with connectives, although there is no significant difference between the realization of reason & cause in Finnish & English. 11 References. N. Uomini", Year=1994} @Article{say-akman97, Author="{Say, Bilge and Akman, Varol}", Title="{Current apporaches to punctuation in computational linguistics}", Journal="Computers and the Humanities", Volume=30, Number=6, Pages="457-469", Abstract="Some recent studies in computational linguistics have aimed to take advantage of various cues presented by punctuation marks. This short survey is intended to summarise these research efforts and additionally, to outline a current perspective for the usage and functions of punctuation marks. We conclude by presenting an information-based framework for punctuation, influenced by treatments of several related phenomena in computational linguistics." Year=1997} @InProceedings{schauer2000, Author="{Schauer, Holger}", Title="{From elementary discourse units to complex ones}", Booktitle="Proceedings of 1st SIGdial Workshop on Discourse and Dialogue", Address="Hong Kong, People's Republic of China", Pages="46-55", Year=2000} @InProceedings{schauer2000b, Author="{Schauer, Holger}", Title="{Referential structure and coherence structure}", Booktitle="Proceedings of 7e conférence annuelle sur le traitement automatique des langues naturelles (TALN 2000)", Address="Lausanne, Switzerland", Pages="327-336", Year=2000} @InProceedings{schauer-hahn2000, Author="{Schauer, Holger and Hahn, Udo}", Title="{Phrases as carriers of coherence relations}", Booktitle="Proceedings of 22nd Annual Conference of the Cognitive Science Society", Address="Philadelphia, Pennsylvania", Pages="429-434", Year=2000} @InProceedings{schauer-hahn2001, Author="{Schauer, Holger and Hahn, Udo}", Title="{Anaphoric cues for coherence relations}", Booktitle="Proceedings of International Euroconference 'Recent Advances in Natural Language Processing', RANLP 2001", Address="Tzigov Chark, Bulgaria", Pages="228-234", Year=2001} @Article{scheppers2003, Author="{Scheppers, F.}", Title="{P(ragmatic)-trees. Coherence, intentionality and cognitive content in discourse and non-verbal action}", Journal="Journal of Pragmatics", Volume=35, Number=5, Pages="665-694", Year=2003} @InProceedings{schilder98, Author="{Schilder, Frank}", Title="{Temporal discourse markers and the flow of events}", Booktitle="Proceedings of COLING-ACL Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="58-61", Year=1998} @InProceedings{schilder98b, Author="{Schilder, Frank}", Title="{An underspecified segmented discourse representation theory}", Booktitle="Proceedings of 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (COLING-ACL'98)", Address="Montréal, Canada", Pages="1188-1192", Year=1998} @InProceedings{schilder2000, Author="{Schilder, Frank}", Title="{Robust text analysis via underspecification}", Booktitle="Proceedings of 1st workshop on RObust Methods in Analysis of Natural language Data (ROMAND 2000)", Address="Lausanne, Switzerland", Pages="105-120", Year=2000} @Article{schilder2002, Author="{Schilder, Frank}", Title="{Robust discourse parsing via discourse markers, topicality and position}", Journal="Natural Language Engineering", Volume=8, Number=2/3, Pages="235-255", Abstract="Claims that current approaches to the automated generation of discourse structures is hampered by theory-dependency. Presents an algorithm which uses a theoretical approach known as Underspecified Segmented Discourse Representation Theory, (USDRT) which is itself a growth out of SDRT and DRT. The gist of USDRT is that the algorithm will never fail to generate tree representation; it is just that any number of the relations at the non-terminal nodes will be left unspecified. Full, accurate diagrams are said to be impossible without either an impossibly large wealth of world knowledge, or some very domain-specific coding." Year=2002} @InCollection{scott-desouza90, Author="{Scott, Donia and de Souza, Clarisse Sieckenius}", Title="{Getting the message across in RST-based text generation}", BookTitle="Current Research in Natural Language Generation", Editor="Dale, Robert and Mellish, Chris and Zock, Michael", Publisher="Academic Press", Address="London", Pages="47-73", Abstract="Presents an apporach to generation that seeks not only to preserve, but actually to enhance the rhetorical aspects of a message. Strongly influenced by psycholinguistic research, and studies of the psychology of memory, viewing stylistics as a matter of cognition as opposed to memory." Year=1990} @Article{scott-etal99, Author="{Scott, Donia and Delin, Judy and Hartley, Anthony}", Title="{Identifying congruent pragmatic relations in procedural texts}", Journal="Languages in Contrast", Volume=1, Number=1, Pages="45-82", Abstract="Presents a methodology for the analysis of comparable corpora in different languages using French, English, and Portuguese instructional texts. Discourse perspecive is examined as it is realised by RST relations. It is demonstrated that the three languages tolerate different levels of ambiguity, and prefer different means of semantic disambiguation. Analysis was performed to aid the automatic generation of texts in multiple languages." Year=1999} @InCollection{scott2001, Author="{Scott, Mike}", Title="{Mapping key words to 'problem' and 'solution'}", BookTitle="Patterns of Text: In Honour of Michael Hoey", Editor="Scott, Mike and Thompson, Geoff", Publisher="John Benjamins", Address="Amsterdam/Philadelphia", Pages="109-127", Year=2001} @InProceedings{seville99, Author="{Seville, Helen}", Title="{Experiments with discourse structure}", Booktitle="Proceedings of 3rd International Workshop on Computational Semantics (IWCS-3)", Address="Tilburg, Netherlands", Pages="233-246", Year=1999} @InProceedings{sharoff-sokolova95, Author="{Sharoff, Serge and Sokolova, Lena}", Title="{Analysis of rhetorical structures in technical manuals and their multilingual generation}", Booktitle="Proceedings of the Workshop on Multilingual Generation (IJCAI'95)", Address="Montréal, Canada", Pages="119-128", Year=1995} @InProceedings{shaw98, Author="{Shaw, James}", Title="{Clause agregation using linguistic knowledge}", Booktitle="Proceedings of 9th International Workshop on Natural Language Generation (IWNLG 9)", Address="Niagra-on-the-Lake, Canada", Pages="138-147", Year=1998} @InProceedings{shinmori-etal2002, Author="{Shinmori, Akihiro and Okumura, Manabu and Marukawa, Yuzo and Iwayama, Makoto}", Title="{Rhetorical structure analysis of Japanese patent claims using cue phrases}", Booktitle="Proceedings of the 3rd NTCIR Workshop", Publisher="National Institute of Informatics", Address="Tokyo, Japan", Year=2002} @Article{sibun92, Author="{Sibun, Penelope}", Title="{Generating text without trees}", Journal="Computational Intelligence", Volume=8, Number=1, Pages="102-122", Year=1992} @InProceedings{sidner93, Author="{Sidner, Candace L.}", Title="{On discourse relations, rhetorical relations and rhetoric}", Booktitle="Proceedings of Workshop on Intentionality and Structure in Discourse Relations, ACL", Publisher="ACL", Address="Ohio State University", Pages="122-124", Year=1993} @Book{siepmann2005, Author="{Siepmann, Dirk}", Title="Discourse Markers across Languages", Publisher="Routledge", Address="New York", Year=2005} @InProceedings{sitter-maier-ecai92, Author="{Sitter, Stefan and Maier, Elisabeth}", Title="{Rhetorical relations in a model of information-seeking dialogues}", Booktitle="10th. European Conference on Artificial Itelligence", Address="Vienna, Austria", Year=1992} @Article{smith2004, Author="{Smith, Caroline L.}", Title="{Topic transitions and durational prosody in reading aloud: Production and modeling}", Journal="Speech Communication", Volume=42, Number=3-4, Pages="247-270", Note="Cited Reference Count: 51 Cited References: *DEN SYST, 1997, CANV 5 US GUID *SAS I, 1998, STATV REF MAN AYERS G, 1994, WORKING PAPERS LINGU, V44, P1 BARBOSA P, 1994, SPEECH COMMUN, V15, P127 BROWN G, 1980, QUESTIONS INTONATION CAMPBELL N, 1990, TALKING MACHINES THE, P211 CAMPBELL N, 2000, PROSODY THEORY EXPT, P281 COHEN J, 1993, BEHAV RES METH INSTR, V25, P257 CRYSTAL TH, 1982, J ACOUST SOC AM, V72, P705 DENOUDEN H, 2000, P 10 ANN M SOC TEXT, P40 EDWARDS J, 1991, J ACOUST SOC AM, V89, P369 EFRON B, 1993, INTRO BOOTSTRAP, P45 FLEISS JL, 1971, PSYCHOL BULL, V76, P378 FON YJJ, 2002, THESIS OHIO STATE U GEE JP, 1983, COGNITIVE PSYCHOL, V15, P411 GROSZ B, 1992, P INT C SPOK LANG PR, P429 GROSZ B, 1986, COMPUTATIONAL LINGUI, V12, P175 HAASE M, 2001, P EUROSPEECH, P2157 HERMAN R, 2000, J PHONETICS, V28, P466 HIRSCHBERG J, 1986, P 24 ANN M ASS COMP, P136 HIRSCHBERG J, 1996, P 34 ANN M ASS COMP, P286 HIRSCHBERG J, 1993, P ESCA WORKSH PROS, P90 JURAFSKY D, 1997, 9702 U COL I COGN SC KOOPMANSVANBEIN.F, 1996, P I PHON SC U AMST, P1 KREIMAN J, 1982, J PHONETICS, V10, P163 LANDIS JR, 1977, BIOMETRICS, V33, P159 LEHISTE I, 1975, STRUCTURE PROCESS SP, P195 LEHISTE I, 1979, FRONTIERS SPEECH COM, P191 LITTELL R, SAS SYSTEM MIXED MOD MANN WC, 1988, TEXT, V8, P243 MUNHALL KG, 1985, J ACOUST SOC AM, V78, P1548 NAKAJIMA S, 1997, COMPUTING PROSODY CO, P81 NAKAJIMA S, 1993, PHONETICA, V50, P197 NAKATANI C, 1996, TR2195 HARV U CTR RE NOORDMAN L, 1999, DISCOURSE STUDIES CO, P133 PASSONNEAU RJ, 1996, COMPUTATIONAL CONVER, P161 SHATTUCKHUFNAGEL S, 1996, J PSYCHOLINGUIST RES, V25, P193 SHRIBERG E, 2000, SPEECH COMMUN, V32, P127 SLUIJTER AMC, 1993, PHONETICA, V50, P180 STIRLING L, 2001, SPEECH COMMUN, V33, P113 SWERTS M, 1997, J ACOUST SOC AM, V101, P514 SWERTS M, 1997, SPEECH COMMUN, V22, P25 SWERTS M, 1994, LANG SPEECH, V37, P21 THORSEN NG, 1985, J ACOUST SOC AM, V77, P1205 TURK AE, 1999, J PHONETICS, V27, P171 UMEDA N, 1975, J ACOUST SOC AM, V58, P434 VANDONZEL M, 1999, PROSODIC ASPECTS INF VANSANTEN JPH, 1994, COMPUT SPEECH LANG, V8, P95 WIGHTMAN S, 1992, J ACOUST SOC AM, V92, P1707 WOUTERS J, 2002, J ACOUST SOC AM 1, V111, P417 YULE G, 1980, LINGUA, V52, P33 Article", Abstract="The linguistic structure of an utterance is known to affect the durational prosody of sounds, words and phrases. There has been increasing interest in how discourse-level organization affects prosody, in part because modeling discourse-level effects could improve the comprehensibility of longer passages of synthesized text. The approach taken here is to look at how topics are sequenced in a text, and how this affects durational prosody when that text is read aloud.Two speakers of American English were recorded reading a set of text materials on 10 separate occasions. Measurements of these recordings indicated that the type of transition in topic between two successive sentences had a significant effect on the amount of sentence-final lengthening, the duration of the pause between sentences, and the speech rate at the end of a sentence and the beginning of the following sentence. These measurements were then used to create a mathematical model of one speaker, and to generate several versions of one of this speaker's original recordings, with each version incorporating different manipulations of the durational patterns and their variability. These versions were played to listeners, who preferred those where the manipulations included durational patterns reflecting the organization of topics in the text. (C) 2003 Elsevier B.V. All rights reserved." Year=2004} @TechReport{smith97, Author="{Smith, Eliot}", Title="{A Computational Model of On-Line Story Understanding}", Institution="University of Birmingham", Type="Thesis Progress Report", Abstract="Cites RST, but really uses DRT as a means of representing discourse structure in a larger framework of modelling the understanding of narrative." Year=1997} @InProceedings{somasundaran-etal2009, Author="{Somasundaran, Swapna and Namata, Galileo and Wiebe, Janyce and Getoor, Lise}", Title="{Supervised and unsupervised methods in employing discourse relations for improving opinion polarity classification}", Booktitle="Proceedings of Conference on Empirical Methods in NLP (EMNLP)", Address="Singapore", Year=2009} @InProceedings{soria-ferrari98, Author="{Soria, Claudia and Ferrari, Giacomo}", Title="{Lexical marking of discourse relations: Some experimental findings}", Booktitle="Proceedings of COLING-ACL Workshop on Discourse Relations and Discourse Markers", Address="Montréal, Canada", Pages="36-42", Year=1998} @InProceedings{soricut-marcu2003, Author="{Soricut, Radu and Marcu, Daniel}", Title="{Sentence level discourse parsing using syntactic and lexical information}", Booktitle="Proceedings of Human Language Technology and North American Association for Computational Linguistics Conference (HLT-NAACL'03)", Address="Edmonton, Canada", Year=2003} @Article{souza2008, Author="{Souza, Edson Rosa Francisco de}", Title="{A noção de discurso em modelos teóricos}", Journal="Signum: Estudos da Linguagem", Volume=11, Number=1, Pages="237-256", Note="Citation of: JofPrags 2006", Year=2008} @PhDThesis{souza2009, Author="Souza, Edson Rosa Francisco de", Title="{Gramaticalização dos itens linguisticos assim, já e aí no português brasileiro: um estudo sob a perspectiva da gramática discursivo-funcional [Grammaticalization of linguistic items assim, ja and ai in Brazilian Portuguese: A functional discourse grammar approach]}", School="Universidade Estadual de Campinas, Brazil", Note="Citation of: JofPrags 2006", Type="PhD dissertation", Year=2009} @InCollection{sparck-jones95, Author="{Sparck-Jones, Karen}", Title="{Discourse modelling for automatic summarising}", BookTitle="Prague Linguistic Circle Papers (Travaux du cercle linguistique de Prague nouvelle série)", Editor="Hajicová, Eva and Cervenka, Miroslav and Leška, Oldrich and Sgall, Petr", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="201-227", Abstract="As part of a research program intended to develop automated systems for summarizing texts, issues in text processing are addressed. The nature of relevant large-scale discourse units exploitable for summaries is explored, & simulation experiments are conducted to compare the output of various summary techniques. Source representations are classified according to the type of information they convey - linguistic, world, or communicative; bottom-up or constructed representation structures are contrasted with top-down or instantiated ones. Results of initial experiments, in which automatic text processing of logical forms of sentences is simulated, are illustrated by a comparison of representation structures & output summaries for a single sample text using (1) bottom-up communicative representations, (2) rhetorical structure theory representations, (3) top-down world-type representations, & (4) text discourse grammar representations. 12 Figures, 31 References. J. Hitchcock", Year=1995} @InProceedings{spenader-lobanova2009, Author="{Spenader, Jennifer and Lobanova, Anna}", Title="{Reliable discourse markers for contrast relations}", Booktitle="Proceedings of the 8th International Conference on Computational Semantics", Address="Tilburg, The Netherlands", Year=2009} @Article{spooren97, Author="{Spooren, Wilbert}", Title="{The processing of underspecified coherence relations}", Journal="Discourse Processes", Volume=24, Pages="149-168", Abstract="Talks about coherence relations that are not explicitly signalled by a cue, or more interestingly, ones which are signalled by a cue whose surface meaning is to signal a different relation. (eg and then for causative, not temporal) The discussion is largely pragmatic, and not too terribly relevant to RST. One cool observation: in the study of the production of such underspecified relations by children, the most common such relation was EVIDENCE, which was the one Marcu and Echihabi's unsupervised approach was best at recognising. Perhaps they are not so underspecified after all? (At least in English)", Year=1997} @Article{spooren-sanders2008, Author="{Spooren, Wilbert and Sanders, Ted}", Title="{The acquisition order of coherence relations: On cognitive complexity in discourse}", Journal="Journal of Pragmatics", Volume=40, Number=12, Pages="2003-2026", Note="Citation of Taboada and Mann 2006, part 2", Abstract="This article presents an analysis of the acquisition order of Coherence relations between discourse segments. The basis is a cognitive theory of coherence relations (Sanders et al., 1992) that makes predictions about the order in which the relations and their linguistic expressions are acquired, because they Show all increasing cognitive complexity. The child language literature lends Support to two distinctions in the theory. Basic Operation (causal versus additive) and Polarity (positive versus negative). In two studies. additional data were collected to test the validity of two other distinctions, Source of Coherence and Order of the Coherence Relation. In the first Study, children described it picture or conversed freely with the investigator Both distinctions turn out to be necessary to account for the acquisition patterns. IN the second study. the children's proficiency in dealing, with negative causal relations was investigated. The two Studies use different research designs. The first is a Study of relatively naturalistic, Only Partially Structured elicitation of extended stretches of speech produced by children, the other is an experiment oil the understanding and production of coherence relations in short sequences of statements relying on nonsense words that lack,I conventional semantic content. The two procedures tap very different kinds of communicative skills and linguistic as well as conceptual knowledge. The combination of these two studies allows LIS to draw Valid Conclusions about the acquisition of the various coherence relations. The data Support the claim that cognitively complex coherence relations show up later than cognitively simple relations. (C) 2008 Elsevier B.V. All rights reserved." Year=2008} @Article{sporleder2007, Author="{Sporleder, Caroline}", Title="{Manually vs. automatically labelled data in discourse relation classification. Effects of example and feature selection}", Journal="LDV-Forum, Journal for Computational Linguistics and Language Technology", Volume=22, Number=1, Pages="1-20", Note="Citation of Murray, Taboada and Renals 2006", Abstract="We explore the task of predicting which discourse relation holds between two text spans in which the relation is not signalled by an unambiguous discourse marker. It has been proposed that automatically labelled data, which can be derived from examples in which a discourse relation is unambiguously signalled, could be used to train a machine learner to perform this task reasonably well. However, more recent results suggest that there are problems with this approach, probably due to the fact that the automatically labelled data has particular properties which are not shared by the data to which the classifier is then applied. We investigate how big this problem really is and whether the unrepresentativeness of the automatically labelled data can be overcome by performing automatic example and feature selection." Year=2007} @InProceedings{sporleder-lapata2005, Author="{Sporleder, Caroline and Lapata, Mirella}", Title="{Discourse chunking and its application to sentence compression}", Booktitle="Proceedings of the 2005 Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP-05)", Address="Vancouver, Canada", Year=2005} @InProceedings{sporleder-lascarides2005, Author="{Sporleder, Caroline and Lascarides, Alex}", Title="{Exploiting linguistic cues to classify rhetorical relations}", Booktitle="Proceedings of Recent Advances in Natural Language Processing (RANLP-05)", Address="Borovets, Bulgaria", Year=2005} @Article{sporleder-lascarides-nle, Author="{Sporleder, Caroline and Lascarides, Alex}", Title="{Using automatically labelled examples to classify rhetorical relations: An assesment}", Journal="Natural Language Engineering", Volume=14, Number=3, Pages="369-416", Abstract="Being able to identify which rhetorical relations (e.g., contrast or explanation) hold between spans of text is important for many natural language processing applications. Using machine learning to obtain a classifier which can distinguish between different relations typically depends on the availability of manually labelled training data, which is very time-consuming to create. However, rhetorical relations are sometimes lexically marked, i.e., signalled by discourse markers (e.g., because, but, consequently etc.), and it has been suggested (Marcu and Echihabi, 2002) that the presence of these cues in some examples can be exploited to label them automatically with the corresponding relation. The discourse markers are then removed and the automatically labelled data are used to train a classifier to determine relations even when no discourse marker is present (based on other linguistic cues such as word co-occurrences). In this paper, we investigate empirically how feasible this approach is. In particular, we test whether automatically labelled, lexically marked examples are really suitable training material for classifiers that are then applied to unmarked examples. Our results suggest that training on this type of data may not be such a good strategy, as models trained in this way do not seem to generalise very well to unmarked data. Furthermore, we found some evidence that this behaviour is largely independent of the classifiers used and seems to lie in the data itself (e.g., marked and unmarked examples may be too dissimilar linguistically and removing unambiguous markers in the automatic labelling process may lead to a meaning shift in the examples)." Year=2008} @InProceedings{stede2004, Author="{Stede, Manfred}", Title="{The Potsdam commentary corpus}", Booktitle="Proceedings of the Workshop on Discourse Annotation, 42nd Meeting of the Association for Computational Linguistics", Address="Barcelona, Spain", Year=2004} @Article{stede2004, Author="{Stede, M.}", Title="{Does discourse processing need discourse topics?}", Journal="Theoretical Linguistics", Volume=30, Number=2-3, Pages="241-253", Year=2004} @Article{stede-rolc2008, Author="{Stede, Manfred}", Title="{Disambiguating rhetorical structure}", Journal="Research in Language and Computation", Volume=6, Pages="311-332", Note="Citation of Taboada and Mann, part 1", Year=2008} @InCollection{stede-rst-nuclearity, Author="{Stede, Manfred}", Title="{RST Revisited: Disentangling nuclearity}", BookTitle="'Subordination' versus 'Coordination' in Sentence and Text", Editor="Fabricius-Hansen, Cathrine and Ramm, Wiebke", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Year=to appear} @InProceedings{stede-heintze, Author="{Stede, Manfred and Heintze, Silvan}", Title="{Machine-assisted rhetorical structure annotation}", Booktitle="Proceedings of International Conference on Computational Linguistics, COLING-04", Address="Geneva, Switzerland", Year=2004} @Article{stede-schmitz2000, Author="{Stede, Manfred and Schmitz, Birte}", Title="{Discourse particles and discourse functions}", Journal="Machine Translation", Volume=15, Number=1-2, Pages="125-147", Year=2000} @InProceedings{stede-umbach98, Author="{Stede, Manfred and Umbach, Carla}", Title="{DiMLex: A lexicon of discourse markers for text generation and understanding}", Booktitle="Proceedings of 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (COLING-ACL'98)", Address="Montréal, Canada", Pages="1238-1242", Year=1998} @Book{stede-etal98, Editor="{Stede, Manfred and Wanner, Leo and Hovy, Eduard}", Title="Proceedings of the Workshop on Discourse Relations and Discourse Markers", Publisher="Association for Computational Linguistics", Address="Montréal, Canada", Year=1998} @Article{steen99, Author="{Steen, Gerard}", Title="{Analyzing metaphor in literature: With examples from William Wordsworth's 'I Wandered Lonely as a Cloud'}", Journal="Poetics Today", Volume=20, Number=3, Pages="499-522", Year=1999} @Article{steen2002, Author="{Steen, Gerard}", Title="{Identifying metaphor in language: A cognitive approach}", Journal="Style", Volume=36, Number=3, Pages="386-407", Abstract="In this article I discuss the ways in which cognitive linguistics can contribute to literary study by showing how both writers and readers make use of implicit cognitive mapping strategies in creating and interpreting literary texts. My argument is based on the premise that the same cognitive processes occur to both produce and understand language. I apply contemporary theories of analogical mapping, conceptual metaphor, and conceptual integration networks (blending) to several Dickinson poems and show how different interpretations of a Dickinson text arise from the different mapping strategies readers use, based on their own idealized cognitive cultural models (knowledge domains)." Year=2002} @Article{steen2004, Author="{Steen, Gerard}", Title="{Can discourse properties of metaphor affect metaphor recognition?}", Journal="Journal of Pragmatics", Volume=36, Number=7, Pages="1295-1313", Abstract="This paper presents an empirical study of metaphor recognition by means of an underlining task in a famous Bob Dylan song, "Hurricane". The paper develops a three-dimensional approach to metaphor processing, in which metaphors are assumed to have linguistic, conceptual, and communicative functions for the construction of a mental representation of the discourse [Understanding Metaphor in Literature: An Empirical Approach, Longman, London, 1994]. A selection of structural metaphor properties for each of these discourse functions is discussed, and predictions are formulated regarding which variables are deemed to boost metaphor recognition. Five of the eight variables are shown to behave according to the predictions. The other three variables are related to each other and do not conform to the expectations. Some possible explanations of the results and suggestions for further research are offered in the conclusion. (C) 2004 Elsevier B.V. All rights reserved." Year=2004} @InProceedings{stent2000, Author="{Stent, Amanda}", Title="{Rhetorical structure in dialog}", Booktitle="Proceedings of First International Conference on Natural Language Generation (INLG'2000)", Address="Mitzpe Ramon, Israel", Pages="247-252", Year=2000} @InProceedings{stent-molina2009, Author="{Stent, Amanda and Molina, Martín}", Title="{Evaluating automatic extraction of rules for sentence plan construction}", Booktitle="Proceedings of the 10th Annual SIGDIAL Meeting on Discourse and Dialogue", Address="London, UK", Pages="290-297", Year=2009} @Article{stevenson-etal2000, Author="{Stevenson, Rosemary and Knott, Alistair and Oberlander, Jon and McDonald, Sharon}", Title="{Interpreting pronouns and connectives: Interactions among focusing, thematic roles and coherence relations}", Journal="Language and Cognitive Processes", Volume=15, Pages="225-262", Year=2000} @PhDThesis{stewart87, Author="Stewart, Anne Merrill", Title="{Clause-Combining in Conchucos Quechua Discourse}", School="University of California Los Angeles", Type="Ph.D. Dissertation", Abstract="Ph.D., UCLA, 1987. Clause-combining in Conchucos Quechua Discourse. 384 pp. [Grammar is seen as ultimately motivated by communicative needs in discourse; texts are seen as networks in which each clause is ultimately interconnected with every other clause through a hierarchy of interacting relations. Particular attention is given to the phenomenon of switch-reference. DAI 48(7):1757-A.] [Order # DA 8723204] 3-88", Year=1987} @InProceedings{subba2007, Author="{Subba, Rajen}", Title="{Exploiting event semantics to parse the rhetorical structure of natural language text}", Booktitle="Proceedings of Doctoral Consortium, North American Association for Computational Linguistics", Address="Rochester, NY", Year=2007} @InProceedings{subba-dieugenio2009, Author="{Subba, Rajen and Di Eugenio, Barbara}", Title="{An effective discourse parser that uses rich linguistic information}", Booktitle="Proceedings of HLT-ACL 2009", Address="Boulder, CO", Pages="566-574", Year=2009} @InProceedings{subba-etal2006, Author="{Subba, Rajen and Di Eugenio, Barbara and Kim, Su Nam}", Title="{Discourse parsing: Learning FOL rules based on rich verb semantic representations to automatically label rhetorical relations}", Booktitle="Workshop "Learning from structured data" at the 11th Conference of European Chapter of the Association for Computational Linguistics", Address="Trento, Italy", Pages="33-40", Year=2006} @InProceedings{sumita-etal92, Author="{Sumita, Kazuo and Ono, Kenji and Chino, T. and Ukita, T. and Amano, S.}", Title="{A discourse structure analyzer for Japanese text}", Booktitle="Proceedings of the International Conference on Fifth Generation Computer Systems", Address="Tokyo, Japan", Pages="1133-1140", Year=1992} @Article{sutcliffe-faraday94, Author="{Sutcliffe, A. and Faraday, P.}", Title="{Systematic Design for Task-Related Multimedia Interfaces}", Journal="Information and Software Technology", Volume=36, Number=4, Pages="225-234", Abstract="Multimedia interfaces are currently created primarily by intuition. Development of a method for analysis and design of multimedia presentation interfaces is described. The study investigates task based information analysis, persistence of information, selection attention and concurrency in presentation. The method gives an agenda of issues, diagrams and techniques for specification, with guidelines for media selection and presentation scripting. Use of the method is illustrated with an example interface from a shipboard emergency management system." Year=1994} @Article{sutcliffe-etal2006, Author="{Sutcliffe, A. G. and Kurniawan, S. and Shin, J. E.}", Title="{A method and advisor tool for multimedia user interface design}", Journal="International Journal of Human-Computer Studies", Volume=64, Number=4, Pages="375-392", Abstract="This paper describes a multimedia user interface design method and a design assistant tool which supports the method. The method covers specification of user requirements and information architecture, selection of appropriate media to represent the information content, design for directing attention to important information and interaction design to enhance user engagement. Guidelines for media selection and design for attractiveness, i.e. usability and user experience, are given. The method was evaluated in a case study design of a crowd control simulation training system, which demonstrated the method was usable and gave good solutions against an expert gold standard design. The tool provides advice on media selection and attention effects that match specification of the information content expressed as information types and communication goals. A usability evaluation was carried out to measure the usefulness and effectiveness of the tool in comparison to the method, and the results showed that the tool has a positive impact on multimedia design. (c) 2005 Elsevier Ltd. All rights reserved." Year=2006} @InProceedings{tsou200, Author="{T’sou, Benjamin K. and Lai, Tom B. Y. and Chan, Samuel W. K. and Gao, Weijun and Zhan, Xuegang}", Title="{Enhancement of a Chinese discourse marker tagger with C 4.5}", BookTitle="Proceedings of the 2nd Chinese Language Processing Workshop, ACL", Address="Hong Kong", Pages="38-45", Year=2000} @PhDThesis{taboada-thesis, Author="Taboada, Maite", Title="{Collaborating through Talk: The Interactive Construction of Task-Oriented Dialogue in English and Spanish}", School="Universidad Complutense", Type="Ph.D. dissertation", Year=2001} @InCollection{taboada-rst-inbook, Author="{Taboada, Maite}", Title="{Rhetorical relations in dialogue: A contrastive study}", BookTitle="Discourse across Languages and Cultures", Editor="Moder, Carol L. and Martinovic-Zic, Aida", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="75-97", Year=2004} @Book{taboada-book, Author="{Taboada, Maite}", Title="Building Coherence and Cohesion: Task-Oriented Dialogue in English and Spanish", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Year=2004} @Article{taboada-dm, Author="{Taboada, Maite}", Title="{Discourse markers as signals (or not) of rhetorical relations}", Journal="Journal of Pragmatics", Volume=38, Number=4, Pages="567-592", Year=2006} @InProceedings{taboada-review-corpus2008, Author="{Taboada, Maite}", Title="SFU Review Corpus", Publisher="Simon Fraser University, http://www.sfu.ca/~mtaboada/research/SFU_Review_Corpus.html", Abstract="A corpus of 400 movie, book, and consumer product reviews from the site Epinions.com. Partially annotated with RST relations and Appraisal labels." Year=2008} @InProceedings{taboada-std2008, Author="{Taboada, Maite}", Title="{Implicit and explicit coherence relations (Invited presentation)}", BookTitle="18th Meeting of the Society for Text and Discourse", Address="Memphis, TN", Year=2008} @InCollection{taboada-discourseofcourse2009, Author="{Taboada, Maite}", Title="{Implicit and explicit coherence relations}", BookTitle="Discourse, of Course", Editor="Renkema, Jan", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="127-140", Year=2009} @Article{taboada-lavid-fol, Author="{Taboada, Maite and Lavid, Julia}", Title="{Rhetorical and thematic patterns in scheduling dialogues: A generic characterization}", Journal="Functions of Language", Volume=10, Number=2, Pages="147-179", Year=2003} @Article{taboada-mann, Author="{Taboada, Maite and Mann, William C.}", Title="{Rhetorical Structure Theory: Looking back and moving ahead}", Journal="Discourse Studies", Volume=8, Number=3, Pages="423-459", Year=2006} @Article{taboada-mann-part2, Author="{Taboada, Maite and Mann, William C.}", Title="{Applications of Rhetorical Structure Theory}", Journal="Discourse Studies", Volume=8, Number=4, Pages="567-588", Year=2006} @InProceedings{taboada-renkema-corpus, Author="{Taboada, Maite and Renkema, Jan}", Title="Discourse relations reference corpus", Publisher="Simon Fraser University and Tilburg University, http://www.sfu.ca/rst/06tools/discourse_relations_corpus.html", Year=2008} @TechReport{taboada-etal-tech-report2008, Author="{Taboada, Maite and Voll, Kimberly and Brooke, Julian}", Title="{Extracting Sentiment as a Function of Discourse Structure and Topicality}", Institution="Simon Fraser University", Number="2008-20", Type="Technical Report", Year=2008} @InProceedings{takeshita-etal-patent07, Author="{Takeshita, Atsushi and Inoue, Takafumi and Tanaka, Kazuo and Nakagawa, Toru}", Title="Method and apparatus for recognizing topic structure of language data", Publisher="Nippon Telegraph and Telephone Corporation", Abstract="A method and apparatus for recognizing the topic structure of language. Language data is divided into simple sentences and a prominent noun portion (PNP) extracted from each. The simple sentences are divided into blocks of data dealing with a single subject. A starting point of at least one topic is detected and a topic introducing region of each topic is determined from block information and language data characteristics. A PNP satisfying a predetermined condition is chosen from the PNPs in each determined topic intro. region as the topic portion (TP) of the topic in the topic intro. region. A topic level indicating a depth of nesting of each topic and a topic scope indicating a region over which the topic continues is determined from the TP and sentences before and after the TP. Sub-topic intro. regions in the remaining area where no topic intro. regions are recognized are determined from block information and language data characteristics. A PNP satisfying a predetermined condition is chosen from the PNPs in each determined sub-topic intro. region as the sub-topic portion (STP) of the sub-topic in the sub-topic intro. region. A temporary topic level indicating a depth of nesting of each sub-topic and a sub-topic scope indicating a region over which the sub-topic continues is determined from the STP and sentences before and after the STP. All determined topics and sub-topics are unified by revising the temporary topic level of each sub-topic according to the topic level of each topic. These topics and their levels are output as a topic structure." Year=1997} @InProceedings{tappe-schilder98, Author="{Tappe, Heike and Schilder, Frank}", Title="{Coherence in spoken discourse}", Booktitle="Proceedings of 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (COLING-ACL'98)", Address="Montréal, Canada", Pages="1294-1298", Year=1998} @Article{taylor2002, Author="{Taylor, P. J.}", Title="{A cylindrical model of communication behavior in crisis negotiations}", Journal="Human Communication Research", Volume=28, Number=1, Pages="7-48", Abstract="This article integrates existing theoretical perspectives on message content and negotiator motivation to formulate a comprehensive definitional model of the interrelationships among communication behaviors in crisis negotiation. A sample of 189 nuclear dialogue spans were transcribed from 9 resolved cases of hostage negotiation and each utterance coded at the level of thought units across 41 behavioral variables. Results of a nonmetric, multidimensional scaling solution provided clear support for the hypothesized cylindrical structure of communication behavior, revealing 3 dominant levels of suspect-negotiator interaction (Avoidance, Distributive, Integrative). At each level of the structure, interactions were found to modulate around 3 thematic styles of communication (Identity, Instrumental, Relational), which reflected the underlying motivational emphasis of individuals' dialogue. Finally, the intensity of communication was found to play a polarizing role in the cylinder, with intense functionally discrete behaviors occurring toward the boundary of the structure." Year=2002} @Article{taylor-donald2004, Author="{Taylor, P. J. and Donald, I.}", Title="{The structure of communication behavior in simulated and actual crisis negotiations}", Journal="Human Communication Research", Volume=30, Number=4, Pages="443-478", Abstract="This research extends recent efforts to differentiate communication in crisis negotiations (Taylor, 2002) by examining how negotiators' behavior differs across context. Data were 108 interaction episodes transcribed from 12 simulated crisis negotiations and coded at the level of thought units across 41 behavioral variables. Results of a smallest space analysis supported the hypothesized differentiation of communication behavior over 3 facets: overall orientation (Avoidance, Distributive, Integrative), motivational concern (Identity, Instrumental, Relational), and intensity (High to Low). This solution was used as a framework for identifying differences in behavior across simulated and actual negotiations. Analyses showed a systematic pattern of variations in behavior use, with simulated negotiations involving relatively more avoidance-relational and distributive-instrumental behavior than actual negotiations. Predictable differences were also observed in the purpose or function of behavior, with highlyintense behaviors showing greater uniformity in function across contexts compared to lowintensity behaviors." Year=2004} @InCollection{tetreault2005, Author="{Tetreault, Joel R.}", Title="{Decomposing discourse}", BookTitle="Anaphora Processing: Linguistic, Cognitive and Computational Modelling", Editor="Branco, António and McEnery, Tony and Mitkov, Ruslan", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="73-95", Year=2005} @InProceedings{teufel-etal99, Author="{Teufel, Simone and Carletta, Jean and Moens, Marc}", Title="{An annotation scheme for discourse-level argumentation in research articles}", Booktitle="Proceedings of 9th Conference of the European Chapter of the Association for Computational Linguistics (EACL'99)", Address="Bergen, Norway", Pages="110-117", Year=1999} @Article{teufel-moens2002, Author="{Teufel, Simone and Moens, Marc}", Title="{Summarizing scientific articles: Experiments with relevance and rhetorical structure}", Journal="Computational Linguistics", Volume=28, Number=4, Pages="409-445", Abstract="In this article we propose a strategy for the summarization of scientific articles that concentrates on the rhetorical status of statements in an article: Material for summaries is selected in such a way that summaries can highlight the new contribution of the source article and situate it with respect to earlier work. We provide a gold standard for summaries of this kind consisting of a substantial corpus of conference articles in computational linguistics annotated with human judgments of the rhetorical status and relevance of each sentence in the articles. We present several experiments measuring our judges’ agreement on these annotations. We also present an algorithm that, on the basis of the annotated training material, selects content from unseen articles and classifies it into a fixed set of seven rhetorical categories. The output of this extraction and classification system can be viewed as a single-document summary in its own right; alternatively, it provides starting material for the generation of task-oriented and user-tailored summaries designed to give users an overview of a scientific field." Year=2002} @Article{thielemann2007, Author="{Thielemann, Nadine}", Title="{Dissension markers and their function in argumentative interaction}", Journal="Zeitschrift für Slawistik", Volume=52, Number=2, Pages="326-352", Note="Citation of Taboada and Mann, part 1", Year=2007} @InProceedings{thione-etal-livetree2004, Author="{Thione, Gian Lorenzo and van der Berg, Martin and Culy, Christopher and Polanyi, Livia}", Title="{LiveTree: An integrated workbench for discourse processing}", Booktitle="Proceedings of the ACL 2004 Workshop on Discourse Annotation", Address="Barcelona, Spain", Year=2004} @InProceedings{thione-etal2004, Author="{Thione, Gian Lorenzo and van der Berg, Martin and Polanyi, Livia and Culy, Christopher}", Title="{Hybrid text summarization: Combining external relevance measures with structural analysis}", Booktitle="Proceedings of the ACL 2004 Workshop Text Summarization Branches Out", Address="Barcelona, Spain", Year=2004} @Article{thomas95, Author="{Thomas, Stephen F.}", Title="{Rhetorical Structure Theory}", Journal="Studies in Machine Translation and Natural Language Processing", Volume=9, Pages="159-174", Abstract="Rhetorical structure theory, as developed by W. C. Mann & S. A. Thompson (eg, 1989), is outlined & evaluated in terms of its relevance for natural language processing at the level of discourse. Historical roots of the theory are traced to the work of R. E. Longacre (1968) on Philippine languages & J. Beekman & J. Callow (1974) on Bible translation. Relations between text spans are defined in terms of nucleus, satellite, writer, & reader; a taxonomy of relations is exemplified, as are possible schemas & schema applications. Discourse analysis procedure is sketched, & features of text structure are illustrated; it is noted that this model has been used successfully in the analysis of hundreds of texts. Computational implementations of rhetorical structure theory in the area of text planning are described; in the absence of structural cues, however, text analysis in this framework depends on the analyst's intuition regarding the writer's intention & therefore resists computerization. 30 References. J. Hitchcock", Year=1995} @Article{thompson2005, Author="{Thompson, G.}", Title="{But me some buts: A multidimensional view of conjunction}", Journal="Text", Volume=25, Number=6, Pages="763-791", Abstract="Although the distinction between 'external' and 'internal' conjunction introduced by Halliday and Hasan (1976) is well established, mainstream studies have, with certain notable exceptions, tended to focus on 'external' types as the core categories and to present 'internal' conjunction as a relatively unmotivated set of pragmatic extensions of the core. The present paper, working within the broad framework of systemic functional linguistics (see, e.g., Halliday and Matthiessen 2004), makes the case for recognizing a more central role for 'internal' conjunction. Current accounts of 'internal' conjunction are reviewed and it is argued that the phenomenon can be defined with more precision than is done at present, even in those models that give it full weight. A more discriminating model of analysis is proposed and related to broader features of the language system. The paper concludes with a discussion of the implications of assigning greater importance to textual and interpersonal dimensions in descriptions of conjunction." Year=2005} @Article{thompson-mann87, Author="{Thompson, Sandra A. and Mann, William C.}", Title="{Rhetorical Structure Theory: A framework for the analysis of texts}", Journal="IPrA Papers in Pragmatics", Volume=1, Number=1, Pages="79-105", Abstract="One of the foundation papers of RST." Year=1987} @InCollection{thompson-mann87b, Author="{Thompson, Sandra A. and Mann, William C.}", Title="{Antithesis: A study in clause combining and discourse structure}", BookTitle="Language Topics: Essays in Honour of Michael Halliday, Volume II", Editor="Steele, Ross and Threadgold, Terry", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="359-381", Abstract="Presents an introduction to RST, then a detailed study of the Antithesis relation." Year=1987} @PhDThesis{timmerman2007, Author="Timmerman, Sander E.J." Title="{Automatic Recognition of Structural Relations in Dutch Text}", School="University of Twente", Note="Citation of Taboada and Mann ('Applications...') and of Journal of Pragmatics 2006", Type="Masters Thesis", Year=2007} @InProceedings{tofiloski-etal-slseg2009, Author="{Tofiloski, Milan and Brooke, Julian and Taboada, Maite}", Title="{A syntactic and lexical-based discourse segmenter}", Booktitle="Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics", Address="Singapore", Pages="77-80", Year=2009} @InCollection{torrance-bouayad-agha2001, Author="{Torrance, Mark and Bouayad-Agha, Nadjet}", Title="{Rhetorical structure analysis as a method for understanding writing processes}", BookTitle="Multidisciplinary Approaches to Discourse", Editor="Degand, Liesbeth and Bestgen, Yves and Spooren, Wilbert and van Waes, Luuk", Publisher="Nodus", Address="Amsterdam", Abstract="Presents an RST-bases means of analyzing text planning. Based upon transcripts of writers "thinking aloud" and their notes while planning a text. The theory is that a proper analysis of the process will give insights into the final result." Year=2001} @Article{trabasso-sperry85, Author="{Trabasso, Tom and Sperry, Linda L.}", Title="{Causal relatedness and importance of story events}", Journal="Journal of Memory and Language", Volume=24, Number=5, Pages="595-611", Abstract="The question of what makes a statement “important” in a story was studied. Causal relations were identified between all pairs of events in six folktales, using context-dependent, logical criteria of necessity, and counterfactual tests of the form: If event A had not occurred, then, in the circumstances of the story, event B would not have occurred. Causal networks were derived from these identifications for each story and two properties of them were found to predict judgments of importance: (1) the number of direct causal connections and (2) whether or not an event was in a causal chain from the opening to the closing of the story. The judged importance of a statement increased with the number of causal connections and causal chain membership. Regression analyses showed that substantial proportions of variance were accounted for jointly by both properties and uniquely by causal connections. The importance of a statement, whether identified by structural analysis or judged by naive subjects, seems to be determined by analogous assessments of the statement's causal and logical relations to other statements in the text." Year=1985} @Book{trail-hale95, Author="{Trail, Ronald L. and Hale, Austin}", Title="A Rhetorical Structure Analysis of a Kalasha Narrative", Publisher="Summer Institute of Linguistics", Address="Horsleys Green", Series="South Asia Work Papers", Year=1995} @InProceedings{traum93, Author="{Traum, David}", Title="{Rhetorical relations, action and intentionality in conversation}", Booktitle="Proceedings of ACL SIG Workshop on Intentionality and Structure in Discourse Relations", Address="Columbus, Ohio", Pages="132-135", Year=1993} @Article{umbach2005, Author="{Umbach, Carla}", Title="{Contrast and information structure: a focus-based analysis of but}", Journal="Linguistics", Volume=43, Number=1, Pages="207-232", Abstract="This article presents a novel analysis of the contrastive connector but based on the observation that (i) the contrast induced by but relates to the information structure of the conjuncts, and (ii) the use of but requires a denial with respect to an implicit question. It is shown that but combines additivity, as in and/also, and exclusion, as in only. This analysis provides a uniform basis to explain the apparently different uses of but, including semantic opposition, denial-of-expectation, and topic change. Moreover, it sheds new light on the concessive use of but." Year=2005} @Article{unger96, Author="{Unger, Christoph}", Title="{The scope of discourse connectives: Implications for discourse organization}", Journal="Journal of Linguistics", Volume=32, Pages="403-438", Abstract="The main aim of this paper is to discuss the claim that discourse connectives are best treated as indicators of coherence relations between hierarchically organized discourse units. It will be argued that coherence relations cannot be seen as cognitively real entities. Furthermore, there is no evidence for hierarchical organization in discourse. The intuitions underlying the notion of hierarchical discourse structure are instead explained in terms of consequences of processing a text in the search for optimal relevance. This account draws attention to a hitherto not widely discussed set of data." Year=1996} @TechReport{uzeda-etal2007, Author="{Uzêda, Vinícius Rodrigues de and Pardo, Thiago Alexandre Salgueiro and Nunes, Maria das Gracas Volpe}", Title="{Estudo e Avaliação de Métodos de Sumarização Automática de Textos Baseados na RST}", Institution="Núcleo Interinstitucional de Lingüística Computacional", Note="Citation of Taboada and Mann, part 1", Number="NILC-TR-07-07", Type="Technical Report", Month="August 2007", Abstract="Neste relatório, apresentamos a investigação e a avaliação de diversos métodos de sumarização automática de textos baseados na RST (Rhetorical Structure Theory), uma das teorias discursivas mais difundidas atualmente. Além de métodos clássicos de sumarização, novos métodos são introduzidos. Conduzimos avaliações comparativas entre os métodos tanto para a língua portuguesa quanto para a inglesa, demonstrando o potencial e as limitações da RST para fins de sumarização." Year=2007} @InProceedings{uzuner-etal2003, Author="{Uzuner, Ozlem and Davis, Randall and Katz, Boris}", Title="Using Discourse-Based Text Features for Evaluating Text Similarity", Publisher="MIT", Pages="8", Note="Does not seem to have been published anywhere yet. Also, this paper has been removed from the first author's webpage (my original download source), so no link is postable." Abstract="Sought information from people on what they use to determine the degree of similarity between texts. Using this, a classifier was trained to recognise similarity based on discourse structure. Based on the works by the first author, this seems to be intended as a plagiarism-detector." Year=2003} @TechReport{van-eijck-kamp96, Author="{van Eijk, Jan and Kamp, Hans}", Title="{Representing Discourse in Context}", Institution="Centrum voor Wiskunde en Informatica", Note="Link is to zipped postscript." Number="CS-R9610", Type="Article for submission", Abstract="This article gives a survey of Discourse Representation Theory (DRT), including recent developments, and with an emphasis on logical issues. Discourse representation structures are defined, and various prespectives on their static and dynamic meaning are discussed. This discussion leads to the study of the process of merging representation structures, a process which can be viewed as a strategy for memory management. Next, a toy example fragment of English is presented, with a compositional DRT semantics. The final sections are devoted to the treatment of quantification and of tense and aspect. The only mention of RST seems to be in the context of stating that the sample of DRT can cope with only relations that are directly signalled on the surface." Year=1996} @Article{vankuppevelt95, Author="{Van Kuppevelt, J.}", Title="{Main structure and side structure in discourse}", Journal="Linguistics", Volume=33, Number=4, Pages="809-833", Abstract="Characteristic for research on the distinction between main structure and side structure in discourse, a distinction that is central to narrative studies, is the absence of uniformity on the notional level. Studies into this distinction have in common that they fail to provide sufficiently adequate criteria to distinguish side structures from substructures, thereby arriving at a rather problematic distinction between main structure and side structure. The aim of this study is twofold: (i) to propose an adequate, formal definition that provides a general identification criterion for distinguishing main structure from side structure in different types of discourse and (ii) to account for the broader concept of main structure that is implied by this definition. This is done by providing an additional criterion for distinguishing between different types of substructures belonging to this part of the discourse: substructures that ultimately define this part and substructures that, while they are relevant to this leading part, form attached elaborations that other authors have considered to be part of the background. Central to this analysis is the basic structuring function of explicit and implicit topic-forming questions in discourse." Year=1995} @Article{vankuppevelt96, Author="{Van Kuppevelt, J.}", Title="{Inferring from topics - Scalar implicatures as topic-dependent inferences}", Journal="Linguistics and Philosophy", Volume=19, Number=4, Pages="393-443", Year=1996} @Article{van-wijk-sanders99, Author="{van Wijk, Carel and Sanders, Ted}", Title="{Identifying writing strategies through text analysis}", Journal="Written Communication", Volume=16, Number=1, Pages="51-75", Abstract="Presents an analysis of an explanatory text written by a 12 year old pupil using the PISA methodology. It is shown that the writer's strategies and procedures can be reconstructed from the PISA analysis, whose hierarchical representation of text is shown to match with the (idiosyncratic) surface punctuation used by the writer." Year=1999} @InProceedings{vanderlinden94, Author="{Vander Linden, Keith}", Title="{Generating precondition expressions in instructional text}", Booktitle="Proceedings of 32nd Annual Meeting of the Association for Computational Linguistics (ACL'94)", Address="Las Cruces, New Mexico", Pages="42-49", Year=1994} @TechReport{vanderlinden-etal92b, Author="{Vander Linden, Keith and Cumming, Susanna and Martin, James H.}", Title="{The Expression of Local Rhetorical Relations in Instructional Text}", Institution="University of Colorado, Boulder", Note="This is a full version of a shorter conference paper presented at ACL and NLG that year." Number="CU-CS-585-92", Type="Technical Report", Abstract="Presents corpus work on the expression of discourse relations in instructional text. This is represented using Systemic Functional Grammar. Looks at the relation between surface grammatical coding and underlying rhetorical structure." Year=1992} @InCollection{vanderlinden-etal92, Author="{Vander Linden, Keith and Cumming, Susanna and Martin, James H.}", Title="{Using system networks to build rhetorical structures}", BookTitle="Aspects of Automated Natural Language Generation", Editor="Dale, Robert and Hovy, Eduard and Rösner, Dietmar and Stock, Oliviero", Publisher="Springer", Address="Berlin", Pages="183-198", Year=1992} @Article{vanderlinden-martin95, Author="{Vander Linden, Keith and Martin, James}", Title="{Expressing rhetorical relations in instructional text: A case study of the purpose relation}", Journal="Computational Linguistics", Volume=21, Number=1, Pages="29-57", Note="There is a duplicate article with the same formatting, dated 1991 issue 0-0 floating around." Abstract="Outlines the steps needed in constructing a text generator, through collection of a corpus for analysis through to algorithm evaluation. This is exemplified by a study of the purpose relation in instructional texts, although the discussion in general is on the generation of rhetorical relations." Year=1995} @InProceedings{verberne-etal2007, Author="{Verberne, Suzan and Boves, Lou and Coppen, Peter-Arno and Oostdijk, Nelleke}", Title="{Exploring discourse structure for Why-QA}", BookTitle="10th International Pragmatics Conference", Address="Göteborg, Sweden", Year=2007} @InCollection{verdejo-daradoumis95, Author="{Verdejo, Felisa and Daradoumis, Thanasis}", Title="{Using rhetorical relations in building a coherent conversational teaching session}", BookTitle="Dialogue and Instruction: Modeling Interaction in Intelligent Tutoring Systems", Editor="Beun, Robbert-Jan and Baker, Michael and Reiner, Miriam", Publisher="Springer", Address="Berlin", Pages="56-71", Year=1995} @InCollection{verhagen2001, Author="{Verhagen, Arie}", Title="{Subordination and discourse segmentation revisited, or: Why matrix clauses may be more dependent than complements}", BookTitle="Text Representation: Linguistic and Psycholinguistic Aspects", Editor="Sanders, Ted and Schilperoord, Joost and Spooren, Wilbert", Publisher="John Benjamins", Address="Amsterdam and Philadelphia", Pages="337-357", Year=2001} @Article{vet99, Author="{Vet, Co}", Title="{Temps verbaux, relations rhetoriques et chaines topicales (Verb tense, rhetorical relations, and topical chains)}", Journal="Travaux de Linguistique", Volume=39, Pages="59-75", Abstract="The factors that determine the interpretation of the order of the eventualities in two sentence fragments of which the first sentence is in the passe simple (perfective past) & the second one in the imparfait (imperfective past) are sought. It is demonstrated that if there is a nominal topical relation between these sentences, the imparfait sentence does not relate to the discourse topic, but to the nominal topic. Despite the rather general interpretation mechanism, the two above-mentioned factors are not capable of predicting all the possible interpretations of this type of fragment: in certain cases, there is a rhetorical relation between the two sentences that overrules the two other interpretative devices. 4 Figures, 24 References. Adapted from the source document", Year=1999} @Article{virtanen95, Author="{Virtanen, Tuija}", Title="{Analysing argumentative strategies: A reply to a complaint}", Journal="Anglicana Turkuensia", Volume=14, Pages="539-547", Abstract="Argumentative strategies are examined in an authentic response by a cereal manufacturer to the complaint of a customer who found a stone in breakfast cereal. The text strategy used included an interactive frame that used first & second person references signaling involvement & a main body that was both integrative & detached. Formal structures used included passives, attributive adjectives, nominalizations, & participles. An analysis of the sample text in terms of rhetorical structure theory indicated that the comprehensive locus of the effect was in the last paragraph. To test this conclusion, native English speakers (N = 6) & a group of nonnative English learners (N = 18) were asked to identify that part of the text that contained the essence of the text; 4 of the 6 native speakers indicated the last paragraph as the most important, supporting the rhetorical structure theory analysis. Variations in the responses suggest that there are different profiles of discourse organization. 1 Figure, 1 Appendix, 20 References. B. Gadalla", Year=1995} @Article{vivanco2005, Author="{Vivanco, Verónica}", Title="{The absence of connectives and the maintenance of coherence in publicity texts}", Journal="Journal of Pragmatics", Volume=37, Number=8, Pages="1233-1249", Abstract="This paper sets out to explore the distinctive features of publicity messages with respect to other kinds of texts. Since the aim of advertising is to point the consumers' ideas in a certain direction, the communicative intention becomes generally constrained by persuasion strategies, such as are studied in pragmatics. Publicity discourse seems to have some specific features which distinguish it from other genres. As regards coherence strategies, previous studies have shown that scientific and technical texts make great use of connectives in order to predict and signal the type of discourse relations and the relation between adjacent elements or sentences. An examination of technical advertisements taken from specialized journals reveals a relatively low number of connectives. In contrast, coherence is maintained with the aid of lexical and semantic resources. Additionally, what we refer to as 'micromarkers' help pinpoint relations. Although these micromarkers have little lexical or semantic content, they are a necessary tool for tying together the concepts they refer to. It turns out that the absence of auxiliary vocabulary, such as connectives, may be an advantage when storing information in the mental reservoir. (c) 2004 Elsevier B.V. All rights reserved." Year=2005} @InProceedings{voll-taboada2007, Author="{Voll, Kimberly and Taboada, Maite}", Title="{Not all words are created equal: Extracting semantic orientation as a function of adjective relevance}", Booktitle="Proceedings of the 20th Australian Joint Conference on Artificial Intelligence", Address="Gold Coast, Australia", Pages="337-346", Year=2007} @Article{wahlster-etal93, Author="{Wahlster, Wolfgang and André, Elisabeth and Finkler, Wolfgang and Profitlich, Hans-Jürgen and Rist, Thomas}", Title="{Plan-based integration of natural language and graphics generation}", Journal="Artificial Intelligence", Volume=63, Number=387-427, Year=1993} @Article{wahlster-etal1991, Author="{Wahlster, W. and Andre, E. and Graf, W. and Rist, T.}", Title="{Knowledge-Based Media Coordination in Intelligent User Interfaces}", Journal="Lecture Notes in Artificial Intelligence", Volume=549, Pages="2-17", Abstract="Multimodal interfaces combining, e.g., natural language and graphics take advantage of both the individual strength of each communication mode and the fact that several modes can be employed in parallel, e.g., in the text-picture combinations of illustrated documents. It is an important goal of this research not simply to merge the verbalization results of a natural language generator and the visualization results of a knowledge-based graphics generator, but to carefully coordinate graphics and text in such a way that they complement each other. We describe the architecture of the knowledge-based presentation system WIP which guarantees a design process with a large degree of freedom that can be used to tailor the presentation to suit the specific context. In WIP, decisions of the language generator may influence graphics generation and graphical constraints may sometimes force decisions in the language production process. In this paper, we focus on the influence of graphical constraints on text generation. In particular, we describe the generation of cross-modal references, the revision of text due to graphical constraints and the clarification of graphics through text." Year=1991} @InProceedings{wahlster-etal91, Author="{Wahlster, Wolfgang and André, Elisabeth and Graf, Winifred and Rist, Thomas}", Title="{Designing illustrated texts: How language production is influenced by graphics generation}", Booktitle="Proceedings of 5th Conference of the European Chapter of the Association for Computational Linguistics (EACL'91)", Address="Berlin, Germany", Pages="8-14", Year=1991} @InProceedings{walker-rambow94, Author="{Walker, Marilyn and Rambow, Owen}", Title="{The role of cognitive modelling in achieving communicative intentions}", Booktitle="Proceedings of 7th International Workshop on Natural Language Generation (IWNLG 7)", Address="Kennebunkport, Maine", Pages="171-180", Year=1994} @Article{walton-reed2005, Author="{Walton, D. and Reed, C. A.}", Title="{Argumentation schemes and enthymemes}", Journal="Synthese", Volume=145, Number=3, Pages="339-370", Note="Cited References: BURKE M, 1985, INFORMAL LOGIC, V7, P107 BURNYEAT MF, 1994, ARISTOTLES RHETORIC, P3 CARBERRY S, 1990, PLAN RECOGNITION NAT COPI IM, 1986, INTRO LOGIC ENNIS RH, INFORMAL LOGIC, V21, P97 ENNIS RH, 1982, SYNTHESE, V51, P61 FARRELL TB, 2000, REREADING ARISTOTLE, P93 FREEMAN JB, 1995, FALLACIES CLASSICAL, P263 GARSSEN B, 2001, CRUCIAL CONCEPTS ARG, P81 GERRITSEN S, 2001, CRUCIAL CONCEPTS ARG, P51 GILBERT M, 1991, INFORMAL LOGIC, V13, P159 GOUGH J, 1985, INFORMAL LOGIC, V7, P99 GOVIER T, 1992, PRACTICAL STUDY ARGU GROARKE L, 1999, ARGUMENTATION, V13, P1 GROARKE L, 2001, P OSSA 2001 C ARG IT HASTINGS AC, 1963, REFORMULATION MODES HINTIKKA J, 1979, ERKENNTNIS, V38, P355 HINTIKKA J, 1992, COMMUN COGNITION, V25, P221 HINTIKKA J, 1993, REV INT PHILOS, V1, P5 HINTIKKA J, 1995, DIALECTICA, V49, P229 HITCHCOCK D, INFORMAL LOGIC NEWSL, V3, P7 HITCHCOCK D, 1985, INFORMAL LOGIC, V7, P83 HURLEY PJ, 2000, CONCISE INTRO LOGIC JACKSON S, 1980, Q J SPEECH, V66, P251 JOHNSON RH, 2000, MANIFEST RATIONALITY JOSEPHSON JR, 1994, ABDUCTIVE INFERENCE KIENPOINTNER M, 1987, ARGUMENTATION LINES, P275 KIENPOINTNER M, 1992, ALLTAGSLOGIK STRUKTU KNEALE W, 1962, DEV LOGIC LENAT D, 1995, COMMUNICATIONS ACM, V38 MANN W, 1987, TEXT, V8 PEIRCE CS, 1965, COLLECTED PAPERS CS, V2 PERELMAN C, 1969, NEW RHETORIC PINTO RC, 1993, PRACTICAL GUIDE CANA PRAKASH J, 2002, ELEC SOC S, V2002, P102 REED C, 1998, P 3 INT C MULT SYST, P246 REED C, 2001, ARAUCARIA SOFTWARE P REITER R, 1980, ARTIF INTELL, V13, P81 SNOECK H, 2001, CRUCIAL CONCEPTS ARG, P101 SRIVEN M, 1976, REASONING VANEEMEREN FH, 1992, ARGUMENTATION COMMUN VERHEIJ B, 1996, THESIS U MAASTRICHT VERHEIJ B, 1999, 7 INT C ART INT LAW, P43 WALTON D, 1996, ARGUMENTATION SCHEME WALTON D, 1997, APPEAL EXPERT OPINIO WALTON D, 2001, PHILOS RHETORIC, V34, P93 Article", Abstract="The aim of this investigation is to explore the role of argumentation schemes in enthymeme reconstruction. This aim is pursued by studying selected cases of incomplete arguments in natural language discourse to see what the requirements are for filling in the unstated premises and conclusions in some systematic and useful way. Some of these cases are best handled using deductive tools, while others respond best to an analysis based on defeasible argumentations schemes. The approach is also shown to work reasonably well for weak arguments, a class of arguments that has always been difficult to analyze without the principle of charity producing a straw man." Year=2005} @Article{webber2004, Author="{Webber, Bonnie}", Title="{D-LTAG: extending lexicalized TAG to discourse}", Journal="Cognitive Science", Volume=28, Number=5, Pages="751-779", Year=2004} @InProceedings{webber-joshi98, Author="{Webber, Bonnie and Joshi, Aravind K.}", Title="{Anchoring a lexicalised Tree-Adjoining Grammar for discourse}", Booktitle="Proceedings of COLING-ACL Workshop on Discourse Markers and Discourse Relations", Address="Montréal, Canada", Pages="86-92", Year=1998} @Article{webber-etal-treebank-intro2005, Author="{Webber, Bonnie and Joshi, Aravind K and Miltsakaki, Eleni and Prasad, Rashmi and Dinesh, Nikhil and Lee, Alan and Forbes, Katherine}", Title="{A short introduction to the Penn Discourse TreeBank}", Journal="Copenhagen Working Papers in Language and Speech Processing", Year=2005} @InProceedings{webber-etal99b, Author="{Webber, Bonnie and Knott, Alistair and Joshi, Aravind K.}", Title="{Multiple discourse connectives in a lexicalised Tree Adjoining Grammar for discourse}", Booktitle="Proceedings of 3rd International Workshop on Computational Semantics", Address="Tilburg, Netherlands", Pages="309-325", Year=1999} @InProceedings{webber-etal99, Author="{Webber, Bonnie and Knott, Alistair and Stone, Matthew and Joshi, Aravind K.}", Title="{Discourse relations: A structural and presuppositional account using lexicalised TAG}", Booktitle="Proceedings of 37th Annual Meeting of the Association for Computational Linguistics", Address="College Park, Maryland", Pages="41-48", Year=1999} @InProceedings{webber-etal99c, Author="{Webber, Bonnie and Knott, Alistair and Stone, Matthew and Joshi, Aravind K.}", Title="{What are little texts made of? A structural and presuppositional account using lexicalised TAG}", Booktitle="Proceedings of International Workshop on Levels of Representation in Discourse (LORID'99)", Address="Edinburgh, UK", Year=1999} @Article{webber-etal2003, Author="{Webber, Bonnie and Stone, Matthew and Joshi, Aravind K. and Knott, Alistair}", Title="{Anaphora and discourse structure}", Journal="Computational Linguistics", Volume=29, Number=4, Pages="545-587", Abstract="Argues that adverbials, generally assumed to signal relations between syntactically connected units work anaphorically to contribute to relational meaning with only indirect dependence on the discourse structure. This provides a "scaffold" for compositional semantics, and shows the multiple ways the relational meaning conveyed anaphorically interact with those derived from structure." Year=2003} @Article{wheatley96, Author="{Wheatley, J.}", Title="{Flowchart representations of genre in professional communication}", Journal="Javnost-the Public", Volume=3, Number=4, Pages="27-38", Year=1996} @InProceedings{wiebe93, Author="{Wiebe, Janyce}", Title="{Issues in linguistic segmentation}", Booktitle="Proceedings of ACL SIG Workshop on Intentionality and Structure in Discourse Relations", Address="Columbus, Ohio", Pages="148-151", Year=1993} @Article{wiebe-etal96, Author="{Wiebe, Janyce and Hirst, Graeme and Horton, D.}", Title="{Language use in context}", Journal="Communications of the ACM", Volume=39, Number=1, Pages="102-111", Year=1996} @Article{wiebe98, Author="{Wiebe, Janyce and O'Hara, T. P. and Ohrstrom-Sandgren, T. and McKeever, K. J.}", Title="{An empirical approach to temporal reference resolution}", Journal="Journal of Artificial Intelligence Research", Volume=9, Pages="247-293", Abstract="Scheduling dialogs, during which people negotiate the times of appointments, are common in everyday life. This paper reports the results of an in-depth empirical investigation of resolving explicit temporal references in scheduling dialogs. There are four phases of this work: data annotation and evaluation, model development, system implementation and evaluation, and model evaluation and analysis. The system and model were developed primarily on one set of data, and then applied later to a much more complex data set, to assess the generalizability of the model for the task being performed. Many different types of empirical methods are applied to pinpoint the strengths and weaknesses of the approach. Detailed annotation instructions were developed and an intercoder reliability study was performed, showing that naive annotators can reliably perform the targeted annotations. A fully automatic system has been developed and evaluated on unseen test data, with good results on both data sets. We adopt a pure realization of a recency-based focus model to identify precisely when it is and is not adequate for the task being addressed. In addition to system results, an in-depth evaluation of the model itself is presented, based on detailed manual annotations. The results are that few errors occur specifically due to the model of focus being used, and the set of anaphoric relations defined in the model are low in ambiguity for both data sets." Year=1998} @InProceedings{williams-power, Author="{Williams, Sandra and Power, Richard}", Title="{Deriving rhetorical complexity data from the RST-DT corpus}", Booktitle="Proceedings of 6th International Conference on Language Resources and Evaluation (LREC)", Address="Marrakech, Morocco", Pages="2720-2724", Year=2008} @InProceedings{williams-reiter2003, Author="{Williams, Sandra and Reiter, Ehud}", Title="{A corpus analysis of discourse relations for natural language generation}", Booktitle="Proceedings of Corpus Linguistics", Address="Lancaster, UK", Pages="899-908", Year=2003} @PhDThesis{williamson-thesis2000, Author="Williamson, Jeanine Mary", Title="{The Vocabulary and Rhetorical Structures in Literary Studies Articles about Molly Bloom: A Description, and Applications for Information Science}", School="The University of North Carolina at Chapel Hill", Type="Ph.D. dissertation", Abstract="The purpose of this research was to intensively study 11 literary studies articles about the fictional character from James Joyce's Ulysses , Molly Bloom. A typology was qualitatively developed for coding word types, and Rhetorical Structure Theory (RST) (Maim & Thompson, 1987) was used to code sentence roles, or functions, such as background, evidence, thesis, etc. A few sentence roles in addition to those found in RST were used. A goal of the study was to develop rules for selecting sentences from the articles to represent them. A number of analyses were done to further this goal: the distributions of word types and sentence role types within the various articles were counted; the occurrences of word types within sentences of particular roles were found; the bigrams (two-word type pairs) within sentences of different sentence roles were counted. In addition, the number of times sentence role types followed other sentence roles was counted, and the agreement (percentage of word types shared) between sentence roles that followed other sentence roles was calculated. Z-scores (Smajda, 1993) were used to determine when bigrams and followed-by pairs were comparatively frequent. A study of the occurrence of actual “phrases” (real combinations of word-types, as opposed to simple co-occurrence pairs, or bigrams) was done. Chi-square goodness of fit tests revealed that in some cases the distributions of actually occurring word combinations across sentence roles differed from the overall distributions of sentence roles. The quantitative results and qualitative observations were used to generate sentence extraction rules. The qualitatively derived rule for macroparadigmatic articles (those which apply a theory to a literary work or discuss it in comparison with another work) (Fahnestock and Secor, 1991) worked better than the quantitatively derived rules, in many cases yielding coherent, not overly concrete extracts that captured main points of the articles. The macroparadigmatic rule and another less satisfactory one for concrete articles were applied to 21 additional articles." Year=2000} @PhDThesis{wolf-diss2004, Author="Wolf, Florian", Title="{Coherence in Natural Language: Data Structures and Applications}", School="MIT", Type="Ph.D. dissertation", Year=2004} @InProceedings{wolf-gibson-ms2004, Author="{Wolf, Florian and Gibson, Edward}", Title="A response to Marcu (2003). Discourse structure: trees or graphs?" Year=2004} @InProceedings{wolf-gibson-acl2004, Author="{Wolf, Florian and Gibson, Edward}", Title="{Paragraph-, word-, and coherence-based approaches to sentence ranking: A comparison of algorithm and human performance}", Booktitle="Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics", Address="Barcelona, Spain", Year=2004} @InProceedings{wolf-gibson-coling2004, Author="{Wolf, Florian and Gibson, Edward}", Title="{Representing discourse coherence: A corpus-based analysis}", Booktitle="Proceedings of the 20th International Conference on Computational Linguistics (COLING)", Address="Geneva, Switzerland", Year=2004} @Article{wolf-gibson-cl2005, Author="{Wolf, Florian and Gibson, Edward}", Title="{Representing discourse coherence: A corpus-based analysis}", Journal="Computational Linguistics", Volume=31, Number=2, Pages="249-287", Abstract="This article aims to present a set of discourse structure relations that are easy to code and to develop criteria for an appropriate data structure for representing these relations. Discourse structure here refers to informational relations that hold between sentences in a discourse. The set of discourse relations introduced here is based on Hobbs (1985). We present a method for annotating discourse coherence structures that we used to manually annotate a database of 135 texts from theWall Street Journal and the AP Newswire. All texts were independently annotated by two annotators. Kappa values of greater than 0.8 indicated good interannotator agreement. We furthermore present evidence that trees are not a descriptively adequate data structure for representing discourse structure: In coherence structures of naturally occurring texts, we found many different kinds of crossed dependencies, as well as many nodes with multiple parents. The claims are supported by statistical results from our hand-annotated database of 135 texts." Year=2005} @Book{wolf-gibson-book-2006, Author="{Wolf, Florian and Gibson, Edward}", Title="Coherence in Natural Language: Data Structures and Applications", Publisher="MIT Press", Address="Cambridge, MA", Year=2006} @Article{wolf-etal2004, Author="{Wolf, Florian and Gibson, Edward and Desmet, Timothy}", Title="{Coherence and pronoun resolution}", Journal="Language and Cognitive Processes", Volume=19, Number=6, Pages="665-675", Year=2004} @InProceedings{wolf-etal-ms2003, Author="{Wolf, Florian and Gibson, Edward and Fisher, Amy and Knight, Meredith}", Title="A procedure for collecting a database of texts annotated with coherence relations", Abstract="A ms that outlines how to annotate texts, and compares it to the RST treebank", Year=2003} @InProceedings{wolf-etal-corpus2005, Author="{Wolf, Florian and Gibson, Edward and Fisher, Amy and Knight, Meredith}", Title="Discourse GraphBank, LDC2005T08", Publisher="Linguistic Data Consortium", Number=LDC2005T08, Year=2005} @PhDThesis{wong-thesis2004, Author="Wong, Cecilia S. M." Title="{Automatic Text Analysis using Rhetorical Structure Theory with application for information search and retrieval}", School="City University of Hong Kong", Type="Ph.D. dissertation", Year=2004} @InProceedings{wong-webster2004, Author="{Wong, Cecilia S. M. and Webster, Jonathan J.}", Title="{Linguistic description and exploration using RDF (Resource Description Framework)}", Booktitle="2001 Joint International Conference of the Association for Computers and the Humanities and the Association for Literary and Linguistic Computing", Address="New York", Year=2001} @Article{ye-etal2007, Author="{Ye, S. and Chua, T. S. and Kan, M. Y. and Qiu, L.}", Title="{Document concept lattice for text understanding and summarization}", Journal="Information Processing and Management", Volume=43, Number=6, Pages="1643-1662", Abstract="We argue that the quality of a summary can be evaluated based on how many concepts in the original document(s) that can be preserved after summarization. Here, a concept refers to an abstract or concrete entity or its action often expressed by diverse terms in text. Summary generation can thus be considered as an optimization problem of selecting a set of sentences with minimal answer loss. In this paper, we propose a document concept lattice that indexes the hierarchy of local topics tied to a set of frequent concepts and the corresponding sentences containing these topics. The local topics will specify the promising sub-spaces related to the selected concepts and sentences. Based on this lattice, the summary is an optimized selection of a set of distinct and salient local topics that lead to maximal coverage of concepts with the given number of sentences. Our summarizer based on the concept lattice has demonstrated competitive performance in Document Understanding Conference 2005 and 2006 evaluations as well as follow-on tests. (C) 2007 Elsevier Ltd. All rights reserved." Year=2007} @Article{yetim94, Author="{Yetim, F.}", Title="{Transparency of Knowledge-Based Systems - State-of-the-Art and Trends in Research in the Field of Explanation Components}", Journal="Nachrichten Fur Dokumentation", Volume=45, Number=5, Pages="291-297", Abstract="Explanation components belong to pragmatic components of knowledge-based systems und are used for making the actions of the system for the user transparent. The research in developing explanation components have made considerable progress. This paper gives a survey of recent developements and shows also research deficiencies." Year=1994} @InCollection{yondem2003, Author="{Yondem, M. T. and Ucoluk, G.}", Title="{A realistic success criterion for discourse segmentation}", BookTitle="Computer and Information Sciences - Iscis 2003", Series="Lecture Notes in Computer Science", Volume=2869, Pages="592-600", Abstract="In this study, compared to the existing one, a more realistic evaluation method for discourse segmentation is introduced. It is believed that discourse segmentation is a fuzzy task [Pas96]. Human subjects may agree on different discourse boundaries, with high agreement among them. In the existing method a threshold value is calculated and sentences that marked by that many subjects are decided as real boundaries and other marks are not been considered. Furthermore automatically discovered boundaries, in case of being misplaced, are treated as a strict failure, disregarding the proximity wrt to the human found boundaries. The proposed method overcomes these shortcomings, and credits the fuzziness of the human subjects' decisions as well as tolerates misplacements of the automated discovery. The proposed method is tunable from crisp/harsh to fuzzy/tolerant on human decision as well as automated discovery handling." Year=2003} @Article{you-rada94, Author="{You, G. N. and Rada, R.}", Title="{A Systematic-Approach to Outline Manipulation}", Journal="International Journal of Human-Computer Studies", Volume=41, Number=3, Pages="283-308", Abstract="The outline (table of contents) of a document provides users with a hierarchical view of the document's logical structure. Outlines reflect a conceptual model and can serve as a cognitive aid in reading and writing hypertext. Outlines may have balance along three dimensions: skeletal, lexical, and semantic. When outlines contain balance, alternative views of the outline are readily imagined. Furthermore, hypertext systems can automatically generate alternative outlines with a modified, depth-first traversal of the hypertext links and nodes. Methods for building and maintaining balanced outlines have been successfully used by writers. Readers are aware of the potential of balance and alternative outlines but lack strategies for utilizing them." Year=1994} @InProceedings{young-moore94, Author="{Young, R Michael and Moore, Johanna D}", Title="{Does discourse planning require a special-purpose planner?}", Booktitle="Proceedings of AAAI Workshop on Planning for Inter-Agent Communication", Address="Seattle, Washington", Year=1994} @InProceedings{yue-feng2005, Author="{Yue, Ming and Feng, Zhiwei}", Title="{Findings in a preliminary study on the rhetorical structure of Chinese TV news reports}", BookTitle="First Computational Systemic Functional Grammar Conference", Address="Sydney, Australia", Year=2005} @InProceedings{zetie96, Author="{Zetie, Kendrik P.}", Title="The Strange Case of the Bumble Bee Which Flew", Volume=2004, Note="Winner of the Science in Print Award (U.K. Institute of Physics (http://www.iop.org/news/0012i.1)", Year=1996} @InProceedings{zhang-etal2002, Author="{Zhang, Zhu and Blair-Goldensohn, Sasha and Radev, Dragomir}", Title="{Towards CST-enhanced summarization}", Booktitle="Proceedings of AAAI 2002", Address="Edmonton, Alberta", Year=2002} @InCollection{zhang-radev2005, Author="{Zhang, Z. and Radev, Dragomir}", Title="{Combining labeled and unlabeled data for learning cross-document structural relationships}", BookTitle="Natural Language Processing - Ijcnlp 2004", Series="Lecture Notes in Computer Science", Volume=3248, Pages="32-41", Abstract="Multi-document discourse analysis has emerged with the potential of improving various NLP applications. Based on the newly proposed Cross-document Structure Theory (CST), this paper describes an empirical study that classifies CST relationships between sentence pairs extracted from topically related documents, exploiting both labeled and unlabeled data. We investigate a binary classifier for determining existence of structural relationships and a full classifier using the full taxonomy of relationships. We show that in both cases the exploitation of unlabeled data helps improve the performance of learned classifiers." Year=2005} @Article{zou-yang2007, Author="{Zou, Hongjian and Yang, Erhong}", Title="{Event counts as elementary unit in discourse annotation}", Journal="Recent Advance of Chinese Computing Technologies", Pages="453-458", Note="Citation of Taboada and Mann 2006, part 1", Abstract="We present a strategy on manual annotation of texts reporting occurrences to reveal the discourse structure. Events are chosen as the elementary units in annotation. The nature and the categories of events in discourse are explored in detail. The extraction of event patterns and annotation of events are also discussed. We have annotated 60 texts according to the method above and the experiment shows about 78% sentences can be annotated in great detail." Year=2007} @InProceedings{zukerman-mcconachy93, Author="{Zukerman, Ingrid and McConachy, Richard}", Title="{An optimizing method for structuring inferentially linked discourse}", Booktitle="Proceedings of 11th National Conference on Artificial Intelligence (AAAI-93)", Address="Washington, DC", Pages="202-207", Year=1993} @InProceedings{zukerman-mcconachy95, Author="{Zukerman, Ingrid and McConachy, Richard}", Title="{Generating discourse across several user models: Maximizing belief while avoiding boredom and overload}", Booktitle="Proceedings of 14th International Joint Conference on Artificial Intelligence (IJCAL'95)", Address="Montréal, Canada", Pages="1251-1257", Year=1995} @Article{zukerman-mcconachy2001, Author="{Zukerman, Ingrid and McConachy, Richard}", Title="{Wishful: A discourse planning system that considers a user's inferences}", Journal="Computational Intelligence", Volume=17, Number=1, Pages="1-61", Year=2001}