IFT6289, Winter 2022

Natural Language Processing with Deep Learning



Time and Place

Tuesdays 9:30am - 11:30am
Online via Zoom

Fridays 3:30pm - 5:30pm
Online via Zoom

Please check the Studium platform for the link to Zoom and Slack workspace of this course.
Note that the lectures will be recorded. The link to each recorded lecture will also be posted on Studium after class.

Instructor

Bang Liu
Office hours: Tuesdays 2:00pm - 4:00pm. (Online via Zoom/Slack workspace. Same meeting room with our lectures)
Email: (firstname.lastname@umontreal.ca)
Teaching Assistant: Suyuchen Wang

Course description

Natural Language Processing (NLP) is a branch of artificial intelligence that deals with the interaction between computers and humans using natural language. It is one of the most important technologies of the information age and is used everywhere: search engines, advertising, chatbots, language translation, virtual agents, and so on. Deep Learning approaches have obtained very high performance across many different NLP tasks in recent years. In this course, students will gain a thorough introduction to the basics of NLP, as well as cutting-edge research in Deep Learning for NLP. We will focus on modern techniques for NLP, as well as introduce the applications in our daily lives. Students are encouraged to do some pretty cool research projects based on NLP techniques, e.g., writing poetry, detecting spam emails, building chatbots, machine reading comprehension, and so on. Through lectures, assignments, and a term project, students will learn the necessary skills to design, implement, and understand their own models for NLP tasks.

Prerequisites

  • Proficiency in Python
    All class assignments will be in Python (e.g., using NumPy and PyTorch). If you have a lot of programming experience but in a different language (e.g. C/C++/Matlab/Java/Javascript), you will probably be fine.
  • College Calculus, Linear Algebra
    You should be comfortable taking (multivariable) derivatives and understanding matrix/vector notation and operations.
  • Basic Probability and Statistics
    You should know the basics of probabilities, gaussian distributions, mean, standard deviation, etc.
  • Foundations of Machine Learning
    If you already have basic machine learning and/or deep learning knowledge, the course will be easier.

Reference Texts

No textbook is required. But the following texts that can be read free online are helpful. The following book is helpful to give you more background about neural networks.

Marking scheme

  • Readings (10%):
    10 readings assignments worth 1% each
  • Assignments (45%):
    3 programming assignments worth 15% each
  • Term project (45%):
    Project proposal (up to 2 pages): 5%
    Midway report (up to 4 pages): 5%
    Final presentation: 5%
    Final report (up to 8 pages): 30%
  • Bonus: class participation (2%):
    Students are encouraged to actively participate in the class, slack, etc.
Late policy:
A late day extends the deadline 24 hours. For ALL assignments, submissions after 2 late days (48 hours) of the deadline won't be accepted.
For programming assignments, we deduct 2% for each late day. We don't count hours, e.g., if you submit an assignment after 25 hours, it will be considered as 2 late days and will be deducted 4%.
For project proposal, midway report, we deduct 1% for each late day.
For project final report, we deduct 3% for each late day.
No late day for the final project presentation and reading assignments.

Tentative Time Table

Note: tentative schedule is subject to change.
Date Topic
Section I: Introduction / background
Lecture 1 Introduction to NLP (Slides)
Lecture 2 Neural Networks and Backpropagation (Slides)
Section II: NLP core techniques
Lecture 3 Language Modeling and Recurrent Neural Networks (Slides)
Lecture 4 Word Meaning and Word Embedding (Slides)
Lecture 5 Sentence Embeddings (Slides)
Lecture 6 Machine Translation, Sequence to Sequence, and Attention (Slides)
Lecture 7 Transformer and BERT (Slides)
Lecture 8 Prompting (Slides)
Lecture 9~11 Pre-trained Language Models, Transformers, and Prompting Techniques (student mini lectures) (Slides)
Lecture 15 Constituency Parsing (Slides)
Lecture 16 Syntactic Dependency Parsing (Slides)
Section III: Cutting-edge research topics.
Lecture 12 Knowledge Graphs: Extracting and Leveraging Meaning from Unstructured Text (Slides)
Lecture 13 GNNs and Graph-based NLP (Slides)
Lecture 14 Invited talk - Creating Interactive Agents with Imitation Learning (Dr. Rui Zhu, DeepMind)
Lecture 17 Open Domain Question Answering (Link)
Lecture 18 Conference tutorial - Neural Approaches to Conversational AI (Link)

Resources

Software

  • PyTorch an open-source deep learning library.
  • DGL an open-source library for deep learning on graphs.
  • HuggingFace Transformers an open-source library containing PyTorch and Tensorflow implementations, pre-trained model weights, usage scripts and conversion utilities for a variety of pre-trained language models.