Fall 2021 - CMPT 413 E100

Computational Linguistics (3)

Class Number: 4656

Delivery Method: In Person

Overview

  • Course Times + Location:

    Tu 5:30 PM – 6:20 PM
    SSCC 9001, Burnaby

    Th 4:30 PM – 6:20 PM
    RCB IMAGTH, Burnaby

  • Prerequisites:

    Completion of nine units in Computing Science upper division courses or, in exceptional cases, permission of the instructor.

Description

CALENDAR DESCRIPTION:

This course examines the theoretical and applied problems of constructing and modelling systems, which aim to extract and represent the meaning of natural language sentences or of whole discourses, but drawing on contributions from the fields of linguistics, cognitive psychology, artificial intelligence and computing science.

COURSE DETAILS:

Imagine a world where you can pick up a phone and talk in English, while at the other end of the line your words are spoken in Chinese. Imagine a computer animated representation of yourself speaking fluently what you have written in an email. Imagine instructing a robot to prepare your backpack for you. Imagine automatically uncovering protein/drug interactions in petabytes of medical abstracts. Imagine feeding a computer an ancient script that no living person can read, then listening as the computer reads aloud in this dead language. Natural Language Processing (NLP) is the automatic analysis of human languages such as English, Korean, and thousands of others analyzed by computer algorithms that can make these applications possible. Unlike artificially created programming languages where the structure and meaning of programs is easy to encode, human languages provide an interesting challenge, both in terms of its analysis and the learning of language from observations. This course is an introduction to NLP and will cover algorithms and techniques for processing text (using probabilistic models and neural networks) as well as basic linguistic concepts. A strong background in math probability, linear algebra, calculus is necessary. Students must also be comfortable with programming and implementing algorithms (coding assignments will be in Python and Pytorch). In addition, familiarity with basic machine learning and deep learning concepts are highly recommended. This course is cross-listed with CMPT 713.

COURSE-LEVEL EDUCATIONAL GOALS:

Topics

  • Text classification
  • Language models
  • Word representations and embeddings
  • Supervised machine learning for NLP
  • Neural models for NLP
  • Sequence modeling
  • Machine translation
  • Parsing and semantics
  • NLP applications

Grading

NOTES:

Grading will be based on assignments, exams, final project and class participation. Details will be announced during the first week of classes.

Students must attain an overall passing grade on the weighted average of exams in the course in order to obtain a clear pass (C- or better).

Materials

MATERIALS + SUPPLIES:

Reference Books

  • Speech and Language Processing (3rd ed), Dan Jurafsky and James H. Martin, 2019, https://web.stanford.edu/~jurafsky/slp3/
  • Neural Network Methods for Natural Language Processing, Yoav Goldberg, Morgan and Claypool, 2017, http://www.morganclaypool.com/doi/10.2200/S00762ED1V01Y201703HLT037
  • Natural Language Processing, Jacob Eisenstein, The MIT Press, 2018, https://github.com/jacobeisenstein/gt-nlp-class/blob/master/notes/eisenstein-nlp-notes.pdf

RECOMMENDED READING:

  • Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville, MIT Press, 2016, https://www.deeplearningbook.org/

Registrar Notes:

ACADEMIC INTEGRITY: YOUR WORK, YOUR SUCCESS

SFU’s Academic Integrity web site http://www.sfu.ca/students/academicintegrity.html is filled with information on what is meant by academic dishonesty, where you can find resources to help with your studies and the consequences of cheating.  Check out the site for more information and videos that help explain the issues in plain English.

Each student is responsible for his or her conduct as it affects the University community.  Academic dishonesty, in whatever form, is ultimately destructive of the values of the University. Furthermore, it is unfair and discouraging to the majority of students who pursue their studies honestly. Scholarly integrity is required of all members of the University. http://www.sfu.ca/policies/gazette/student/s10-01.html

TEACHING AT SFU IN FALL 2021

Teaching at SFU in fall 2021 will involve primarily in-person instruction, with approximately 70 to 80 per cent of classes in person/on campus, with safety plans in place.  Whether your course will be in-person or through remote methods will be clearly identified in the schedule of classes.  You will also know at enrollment whether remote course components will be “live” (synchronous) or at your own pace (asynchronous).

Enrolling in a course acknowledges that you are able to attend in whatever format is required.  You should not enroll in a course that is in-person if you are not able to return to campus, and should be aware that remote study may entail different modes of learning, interaction with your instructor, and ways of getting feedback on your work than may be the case for in-person classes.

Students with hidden or visible disabilities who may need class or exam accommodations, including in the context of remote learning, are advised to register with the SFU Centre for Accessible Learning (caladmin@sfu.ca or 778-782-3112) as early as possible in order to prepare for the fall 2021 term.