Natural language processing (NLP) is a set of methods for making human language accessible to computers. NLP underlies many technologies we use on a daily basis including automatic machine translation, search engines, email spam detection, and automated personalized assistants. These methods draw from a combination of algorithms, linguistics and statistics. This course will provide a foundation in building NLP models to classify, generate, and learn from text data.
Note: This is a tentative schedule and subject to change.
For readings, we will primarily use Jurafsky & Martin, Speech and Language Processing, 3rd edition (J&M). This textbook edition is available online for free here. Other readings will be linked on this page or distributed via Piazza.
| Week | Dates | Theme & Lecture Materials | Readings | Deliverables |
|---|---|---|---|---|
| 0 | Feb 3 | Introduction
[slides] |
|
|
| 1 | Feb 6, 8, 10 | Text Processing
[slides] [slides-solutions] [command-line-demo] [regex tokenization html ipynb] |
|
HW0: Preliminaries
Released: Mon, Feb 6 Due: Thurs, Feb 9 at 9:59pm |
| 2 | Feb 13, 15
[Feb 17 - No class, Winter Carnival] |
Language Modeling and Naive Bayes
[slides][slides-solutions] [ngrams.pdf] [naive-bayes.pdf] [shakespeare ngrams html ipynb] |
|
HW1: Spam via Regular Expressions
Released: Mon, Feb 13 Due: Thurs, Feb 16 at 9:59pm |
| 3 | Feb 20, 22, 24 | Logistic Regression
[slides] [slides-solutions] [logreg.pdf] [numpy html ipynb] |
|
HW2: Naive Bayes
Released: Mon, Feb 20 Due: Fri, Feb 24 at 3:59pm ET |
| 4 | Feb 27 Mar 1, 3 |
Vector Semantics
[slides] [slides-solutions] [numpy vectorizing html ipynb] [vector-semantics.pdf] |
|
HW3: Logistic Regression
Released: Mon, Feb 27 Due: Fri, Mar 3 at 3:59pm ET |
| 5 | March 6, 8, 10 | Deep Learning for NLP
[slides] [slides-solutions] [computation graphs, solutions] [backprop html ipynb] [pytorch html ipynb] [pretrained html ipynb] |
|
HW4: Vector Semantics
Released: Mon, Mar 6 Due: Fri, Mar 10 at 3:59pm ET |
| 6 | Mar 13, 15
[Mar 17 - No class due to midterm] |
Monday - Wrap-Up Deep Learing
Wednesday - Project Logistics & Midterm Review Thursday March 16, Evening Midterm 6-9:30pm (materials thru HW4) [Midterm Guide] |
|
Project: Group preference form
Due: Sunday (3/19) at 10pm ET |
| Mar 18 - April 2 | Spring Break | |||
| 7 | Apr 3, 5, 7 | Dialogue systems and Transformers
[slides] |
|
HW5: Deep Learning for NLP
Released: Mon, Apr 3 Due: Fri, Apr 7 at 3:59pm ET Project: Topic selection form Due: Sun, Apr 9 at 9:59pm ET Project: Scheduling form Due: Sun, Apr 9 at 9:59pm ET |
| 8 | Apr 10-14 | Lecture time: Flipped classroom, project work
[slides] |
HW6: Chat Bots (Groups)
Released: Weds, April 12 Checkpoint (Parts 1&2): Fri, April 21 at 3:59pm ET Due: Fri, Apr 28 at 3:59pm ET (*no late submissions) Project: Mini-lectures next week |
|
| 9 | Apr 17-21 | Lecture time: Student Mini-Lectures
[schedule] [announcement slides] |
Project: Annotated Bibliography
Due: Sun Apr 23 at 9:59pm ET |
|
| 10 | Apr 24-28 | No full-class lecture. Distributed project meetings with Katie
[schedule alternative view] |
Project: Outline
Due: Sun Apr 30 at 9:59pm ET |
|
| 11 | May 1-5 | No full-class lecture. Distributed project meetings with Katie |
Project: Code for Code Review
Due: Sun May 7 at 9:59pm ET |
|
| 12 | May 8-12 | No full-class lecture. Distributed project meetings with Katie
Project Poster Session Bronfman Auditorium Thurs May 11, 6-8pm |
Final Project Completed Final report to Gradescope Due: May 19, 4pm |
|