Link Search Menu Expand Document

CSE 447: Natural Language Processing, Autumn 2026

MWF 3:30–4:20 PM, MGH 389

Announcements

Oct 1: Homework 0 (optional) is out

This is an optional homework and is mainly there for you to revise Python fundamentals and get a basic introduction to PyTorch. There is an extra credit of 2% of the final grade upon the successful completion of this project.

Profile picture for Yulia Tsvetkov

Instructor: Yulia Tsvetkov

yuliats@cs.washington.edu

OH: available on Zoom by appointment.

Profile picture for Kabir Ahuja

Head Teaching Assistant: Kabir Ahuja

kahuja@cs.washington.edu

Office Hours: Wednesday, 10:30–11:30 AM, CSE 1 218 · Zoom

Profile picture for Arohan Agate

Teaching Assistant: Arohan Agate

aagate@cs.washington.edu

Office Hours: Tuesday, 1:00–2:00 PM, Gates 131 · Zoom

Profile picture for Jacqueline He

Teaching Assistant: Jacqueline He

jyyh@cs.washington.edu

Office Hours: Wednesday, 4:30–5:30 PM, Gates 287 · Zoom

Profile picture for Daniel Kim

Teaching Assistant: Daniel Kim

jwonkim@cs.washington.edu

Office Hours: Friday, 9:30–10:30 AM, Gates 150 · Zoom

Profile picture for Lev Kochergin

Teaching Assistant: Lev Kochergin

levkoch@cs.washington.edu

Office Hours: Monday, 2:30–3:30 PM, Allen 2nd-floor breakout area · Zoom

Profile picture for Sheldon Li

Teaching Assistant: Sheldon Li

yongkang@cs.washington.edu

Office Hours: Thursday, 10:00–11:00 AM PST, Allen 220 · Zoom

Profile picture for Yike Wang

Teaching Assistant: Yike Wang

yikewang@cs.washington.edu

Office Hours: Schedule via email for quiz queries.

Summary

This course covers methods for designing systems that intelligently process natural language text data. Topics include language models, text categorization, syntactic and semantic analysis, and machine translation, with an emphasis on algorithms and data-driven methods. The course is hands-on and project-based, focusing on building and evaluating practical NLP systems.

Prerequisites
CSE 312 and CSE 332; recommended: MATH 208. CSE 446 is recommended before or concurrently.

Calendar

The schedule is subject to change.

Week Lecture Date Topic Readings Quiz Homework
1 1 9/30 Logistics
[slides]
Course website and syllabus
2 10/2 Introduction
[slides]
J&M, Chapter 1 HW0 out
2 3 10/5 Linguistics background
[slides]
J&M, Chapter 2
4 10/7 HW1 overview, Quiz overview HW1 out & HW1 overview
5 10/9 Linguistics background
[slides]
J&M, Chapter 2
3 6 10/12 Text classification J&M, Chapter 4 In-class quiz 1
7 10/14 Text classification Pang et al. (2002); Ng & Jordan (2001)
8 10/16 Text classification
4 9 10/19 Text classification J&M, Chapter 4 In-class quiz 2
10 10/21 Text classification J&M, Chapter 4
11 10/23 Text classification J&M, Chapter 4
5 12 10/26 Language modeling J&M, Chapter 3 In-class quiz 3
13 10/28 Language modeling J&M, Chapter 3
14 10/30 Language modeling J&M, Chapter 3 HW1 due
6 15 11/2 Lexical semantics J&M, Chapter 5 In-class quiz 3 HW2 out
16 11/4 Distributional semantics J&M, Chapter 5
17 11/6 Distributional semantics J&M, Chapter 5
7 18 11/9 Neural networks J&M, Chapter 6; Optional — J&M, Chapter 14 In-class quiz 4
19 11/11 Neural networks: Transformers J&M, Chapter 7
20 11/13 LLMs — Pretraining and in-context learning J&M, Chapter 7
8 21 11/16 LLMs — Finetuning J&M, Chapter 8 In-class quiz 5
22 11/18 LLMs — Decoding, beam search, and sampling J&M, Chapter 7
23 11/20 LLMs — Prompting and chain-of-thought The Prompt Report; arXiv:2402.13116; arXiv:2305.16635 HW2 due
9 24 11/23 LLMs — Post-training and alignment J&M, Chapter 8 In-class quiz 6 HW3 out
25 11/25 AI agents
11/27 Thanksgiving — no class
10 26 11/30 NLP in industry: Recommender systems and online training
27 12/2 LLM safety Risks of LLMs, SafetyPrompts, and The Art of Saying No
28 12/4 Conclusion In-class quiz 7
11 12/7 Cancelled .
12/9 Cancelled HW3 due
12/11 Cancelled

Resources

  • Readings
    • J&M III: Speech and Language Processing (Dan Jurafsky and James H. Martin)
    • Additional readings will be released weekly.

Course Policy

Please note that the quizzes are mandatory to be taken from the classroom in person only. Quizzes taken from home won’t be graded. Quizzes are closed-book: you are not allowed to refer to your notes, the textbook, or any AI tools during the quiz. Please let us know in advance if there are any DRS-related accommodations to be made for you. Students are expected to attend all classes in person. While we will try our best to have recordings available for the class, in-person attendance is expected.

You are encouraged to use AI for general questions and for brainstorming, clarification, and refinement on course work, but you may not use AI to substantially create the work for you. AI can be helpful for exploring ideas and improving drafts, provided your submitted work remains your own. We highly recommend going through UW’s vice provost for AI shares what every UW student should know about AI to learn how to make thoughtful judgments about when and how to use AI.

We will have oral exams after assignment submissions that will test your knowledge of your submitted solutions. A grade for an assignment will be awarded only if you pass its oral exam.

Note to Students

Take care of yourself! As a student, you may experience a range of challenges that can interfere with learning, such as strained relationships, increased anxiety, substance use, feeling down, difficulty concentrating and/or lack of motivation. All of us benefit from support during times of struggle. There are many helpful resources available on campus and an important part of having a healthy life is learning how to ask for help. Asking for support sooner rather than later is almost always helpful. UW services are available, and treatment does work. You can learn more about confidential mental health services available on campus here. Crisis services are available from the counseling center 24/7 by phone at +1 (866) 743-7732 (more details here).