Natural Language Processing Fall 2020
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
speaking fluently what you have written in an email. 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
Imagine a computer that can do better than humans at answering
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.
- Ali Gholami,
gholami, Office hour: Time: Mon 3-4pm.
- Sonia Raychaudhuri,
sraychau, Office hour: Time: Thurs 3-4pm.
- Yue Ruan,
yuer, Office hour: Time: Tues 3-4pm.
Asking for help
- Ask for help on piazza
- Instructor office hours: Time: Wed 2-3pm
- No emails to the TAs and strictly emails about personal matters to the instructor
- Use only SFU email address and use either
cmpt825: as subject prefix
Time and place
Course lectures will be held using canvas BB Collaborate Ultra
- Wed 11:30am-12:20pm Online
- Fri 10:30am-12:20pm Online
- Last day of classes: Dec 4, 2020
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 (STAT 270)
- Basic Machine Learning (CMPT 419/726) is strongly recommended
There will be optional TA led tutorials that will help review these topics.
- No required textbook. Online readings provided in Syllabus.
- Many of the readings will be from the following:
- Submit homework source code and check your grades on Coursys
- Programming setup and diagnostic homework (2%)
- Four homeworks (60% total - 15% each, with 10% for programming and 5% for question answering). Due dates:
- HW1 on Sept 30, 2020
- HW2 on Oct 14, 2020
- HW3 on Oct 28, 2020
- HW4 on Nov 11, 2020
- Final Project (35% total)
- Project Proposal: Due on Oct 23, 2020 (5%)
- Project Milestone: Due on Nov 20, 2020 (5%)
- Project “Poster” Presentation: Online on Dec 4, 2020 (5%)
- Project Report and Code: Due on Dec 8, 2020 (20%)
- Participation: Helping other students on the discussion board in a positive way (3%)