Fall 2017 - CMPT 882 G100

Special Topics in Artificial Intelligence (3)

Neural Machine Translation

Class Number: 8317

Delivery Method: In Person

Overview

  • Course Times + Location:

    Sep 5 – Dec 4, 2017: Mon, Wed, 2:30–3:50 p.m.
    Burnaby

Description

COURSE DETAILS:

This is a special topics course entitled "Neural Machine Translation". This is an advanced graduate seminar course is about recursive neural network models for machine translation (for natural languages such as English, Chinese, Tagalog, etc.). You will require some background in NLP. The main goal of the course will be to do original research on encoder-decoder recursive neural networks. The course will cover recent developments in neural machine translation and we hope to discuss and solve current limitations of NMT.

Topics

  • Statistical machine translation
  • Neural network feature functions in SMT
  • Neural language models
  • Training recursive neural networks
  • Encoder-decoder networks
  • Attention
  • Extensions to Attention
  • Convolutional networks in NMT
  • Reinforcement learning ideas applied to NMT

Grading

NOTES:

60% for in class presentations. 40% for final project. There is no midterm or final exam.

Graduate Studies Notes:

Important dates and deadlines for graduate students are found here: http://www.sfu.ca/dean-gradstudies/current/important_dates/guidelines.html. The deadline to drop a course with a 100% refund is the end of week 2. The deadline to drop with no notation on your transcript is the end of week 3.

Registrar Notes:

SFU’s Academic Integrity web site http://students.sfu.ca/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

ACADEMIC INTEGRITY: YOUR WORK, YOUR SUCCESS