Natural Language Processing Spring 2025

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 a computer writing new poetry and stories from a prompt or generating art based on descriptions. 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. Imagine a computer that can do better than humans at answering questions.

Natural Language Processing is the automatic analysis of human languages such as English, Korean, and thousands of others analyzed by computer algorithms. 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.

Instructor

• Angel Chang

Teaching Assistants

• Austin Wang, atw7, Office hour: Thu 1:00pm-2:00pm (ASB9808).
• Han-Hung Lee, hla300, Office hour: Tue 2:00pm-3:00pm (ASB9810).
• Xiaohao Sun, xsa55, Office hour: Tue 2:00pm-3:00pm (ASB9810).
• Chuanqi Tang, cta156, Office hour: Thu 1:00pm-2:00pm (ASB9808).

Asking for help

• Ask for help on Coursys Discussion Forum
• Instructor office hours: Wed 1:30pm-2:30pm
• No emails to the TAs and strictly emails about personal matters to the instructor
• Use only SFU email address and use either cmpt413: orcmpt713: as subject prefix
• Always post to the Coursys Discussion Forum instead of email. If you have to email use your SFU email address only.

Time and place

Course lectures will be held in person at the Burnaby campus

• Mon 3:30-4:50pm B9200
• Wed 3:30-4:50pm B9200
• Last day of classes: Apr 9, 2025

Links to course material will be made available on Coursys.

Prerequisites

There are no formal prerequisites for this class. However, you are expected to be familiar with the following:

• Proficiency in Python - Programming assignments will be in python (numpy and pytorch will be used).
• Calculus and Linear Algebra (MATH 151, MATH 232/240) - You will need to be comfortable with taking multivariable derivatives
• Basic Probability and Statistics (CMPT 210 or STAT 270)
• Basic Machine Learning (CMPT 410/726) is strongly recommended (Note: CMPT 410 was previously offered as CMPT 419 under the title “Machine Learning”)

There will be optional TA led tutorials that will help review these topics.

Textbook

• No required textbook. Online readings provided in Syllabus.
• Many of the readings will be from the following:
  • Speech and Language Processing by Dan Jurafsky and James Martin.
  • Natural Language Processing by Jacob Eisenstein
  • A Primer on Neural Network Models for Natural Language Processing by Yoav Goldberg (see also Neural Network methods for Natural Language Processing).

Grading

• Submit homework source code and check your grades on Coursys
• Programming setup and diagnostic homework (5%)
  • HW0 due on Jan 15, 2025
• Four homeworks (64% total - 16% each, with 8% for programming and 8% for question answering). Due dates:
  • HW1 on Jan 29, 2025
  • HW2 on Feb 12, 2025
  • HW3 on Feb 26, 2025
  • HW4 on Mar 12, 2025
• Final Project (28% total)
  • Project Proposal: Due on Feb 24, 2025 (5%)
  • Project Milestone: Due on Mar 20, 2025 (5%)
  • Project “Poster” Presentation: Video due on Apr 6, 2025 (5%)
  • Project Report and Code: Due on Apr 10, 2025 (13%)
• Participation: Helping other students on the discussion board in a positive way (3%)