CMSC 25700/35100: Natural Language Processing

Logistics

• Lectures: Tuesdays/Thursdays 11-12:20, Ryerson 251
• Office hours: (DSI -> 5460 University Ave)
  • Chenhao Tan: Thursdays 2-3pm (DSI 321)
  • Qirun Dai: Wednesdays 11am-1pm (DSI 363)
  • Dang Nguyen: Mondays 11am-12pm, Fridays 3-4pm (DSI 363)
  • Darin Keng: Thursdays 3-5pm (DSI 363)
• Contact: Email (chenhao@uchicago.edu, dangnguyen@uchicago.edu, qirundai@uchicago.edu, dkeng@uchicago.edu); Ed Discussion Forum on Canvas; Discord server (link on Canvas).

Content

What is this course about?

This course will introduce fundamental concepts in natural language processing (NLP). It will cover the basics of enabling computers to understand and generate language, including word embeddings, language modeling, transformers, and an overview of large language models. It will also cover topics on connections with other disciplines such as linguistics and other social sciences.

Prerequisites

• Proficiency in Python

  You should have a strong foundation in Python and familiarity with Git and Jupyter Notebook. In addition, you must be able to quickly learn and adapt to new frameworks. The course will involve using the PyTorch framework, the HuggingFace library, and several APIs (e.g., OpenAI and TogetherAI). Although optional tutorial sessions will be provided to introduce the basics, you are expected to be able to learn from documentation and troubleshoot effectively.

• Calculus, Linear Algebra and Probability

  You should be comfortable taking (multivariable) derivatives, understanding matrix/vector notation and operations, and the basics of probability.

• Machine Learning

  You should have taken one of CMSC 25300, CMSC 25400, and CMSC 25025.

Coursework

Assignments

• Assignment 1: TBD
• Due: Tuesday, January 13, 2026
• Assignment 2: TBD
• Due: Friday, January 23, 2026
• Assignment 3: TBD
• Due: Friday, February 6, 2026
• Assignment 4: TBD
• Due: Friday, February 20, 2026

Project

• Project Proposal: Due Week 5
• Weekly Blog Entries: Weeks 7, 8, 9
• Final Project Presentation: Week 9

Exams

• Midterm: Week 5
• Final Exam: Week 10

Compute

Modal has generously offered compute to each student. See details on Ed.

Textbook

There are a lot of resources online for related content. We will provide readings and pointers throughout the course. A recommended textbook is Speech and Language Processing by Dan Jurafsky and James H. Martin.

Honor Code

We expect students to not look at solutions or implementations online. Like all other classes at UChicago, we take academic honesty very seriously. Please make sure to read the UChicago Academic Honesty page.

Collaboration policy

For individual assignments, collaboration with fellow students is encouraged as long as they are properly disclosed for each submission. However, you should not share any written work or code for your assignments. After discussing a problem with others, you should write the solution by yourself. For final projects, you are expected to work in groups 2-3.

AI tools policy

Using generative AI tools such as Claude Code and ChatGPT is allowed as long as they are properly disclosed for each submission. For individual assignments, we encourage you to implement it on your own so that it maximizes your learning, but learning the content with AI tools is acceptable. In fact, we encourage your creative use of these tools, treating them as collaborators in the learning process.

Additional course policies can be found on Canvas.

Submitting Coursework

• All coursework should be submitted via Gradescope by the deadline.

Late Days

• Each student has 6 late days to use throughout the quarter.
• Each assignment can use at most 3 late days.

Preliminary Schedule

#	Date	Topic	Materials	Deadlines
1	Tues Jan 6	Introduction and tokenization	lecture, notebook(html version)	Assignment 1 out
2	Thurs Jan 8	Word vectors	lecture, notebook(html version) Readings: Efficient Estimation of Word Representations in Vector Space by Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean
3	Tues Jan 13	Text Classification		Assignment 1 due (Tuesday night) Assignment 2 out
4	Thurs Jan 15	N-gram Language Modeling, Neural Language Models
5	Tues Jan 20	The NLP Recipe		Assignment 3 out
6	Thurs Jan 22	Attention		Assignment 2 due (Friday night)
7	Tues Jan 27	Transformers
8	Thurs Jan 29	Pretraining and modern NLP pipeline
9	Tues Feb 3	Benchmarks and Evaluation		Assignment 4 out
10	Thurs Feb 5	Midterm		Assignment 3 due (Friday night) Project Proposal due (Friday night)
11	Tues Feb 10	Decoding LLMs
12	Thurs Feb 12	Prompting
13	Tues Feb 17	Post-training
14	Thurs Feb 19	Reasoning and Agents		Assignment 4 due (Friday night) Blog Entry 1 due
15	Tues Feb 24	Guest Lecture: Hypothesis Generation with Large Language Models
16	Thurs Feb 26	Guest Lecture: Multimodal NLP		Blog Entry 2 due
17	Tues Mar 3	Alignment and Safety
18	Thurs Mar 5	Final Project Presentation		Blog Entry 3 due
19	TBD	Final Exam

Acknowledgments

This course website is adapted from the Stanford CS336 course website. This course is built on prior offerings by Mina Lee and Chenhao Tan.