Skip to main content Link Menu Expand (external link) Copy Copied
CS 288

Advanced Natural Language Processing

Spring 2027

Instructor: Sewon Min
Class hours: TuThu 11:00-12:30 (11:10-12:30 considering Berkeley time)
Class location: Gateway 1220
Instructor OH: TBA
GSI OH: TBA
Contact:

[Ed link: TBA] [Gradescope link: TBA] [Lecture recordings: TBA] [Final project logistics and reference topics: TBA]

Enrollment for students who cannot enroll directly: Please submit the Spring 2027 enrollment form by January 19 to be considered for enrollment. Enrollment depends on seat availability and is not guaranteed. Applicants should generally have A or A+ grades in at least three of CS 188, CS 189, CS 126, CS 127, CS 182, and CS 183, or have Berkeley research or project experience. All information needed is included in the form. Enrollment will be finalized no later than January 29; before then, please do not email to request an early decision.

This course provides a graduate-level introduction to Natural Language Processing (NLP), covering techniques from foundational methods to modern approaches. We begin with core concepts such as word representations and neural network–based NLP models, including recurrent networks and attention mechanisms. We then study modern Transformer-based models, focusing on pre-training, fine-tuning, prompting, scaling laws, and post-training. The course concludes with recent advances in NLP, including retrieval-augmented models, reasoning models, and multimodal systems involving vision and speech.

Prerequisites: CS 288 assumes prior experience in machine learning and proficiency in PyTorch. Students should be familiar with neural networks, PyTorch, and NumPy; no introductory tutorials will be provided.

Schedule (Tentative)

All deadlines are at 5:59 PM Pacific Time.

01/19 Tue
Introduction & n-gram LM
Assignment 1 released
01/21 Thu
Word representation
01/26 Tue
Text classification
01/28 Thu
Sequence models (Key concepts: Recurrent neural networks)
02/02 Tue
Sequence-to-sequence models
Assignment 1 due Team matching request due
02/04 Thu
Sequence-to-sequence models (cont’d)
02/09 Tue
Transformers
Assignment 2 released
02/11 Thu
Transformers (cont’d)
02/16 Tue
Pre-training, Fine-tuning, & Prompting
02/18 Thu
Pre-training, Fine-tuning, & Prompting (cont’d)
02/23 Tue
Post-training
Assignment 2 due
02/25 Thu
Inference methods
03/02 Tue
Evaluation
Project Checkpoint 1 (abstract) due Assignment 3 released
03/04 Thu
Retrieval and RAG
03/09 Tue
Guest lecture (TBA)
03/11 Thu
Advanced topic: Scaling laws & data
03/16 Tue
Advanced topic: Advanced architectures
Assignment 3 early milestone due
03/18 Thu
No class: EECS faculty retreat (expected)
Assignment 3 due
03/23 Tue
No class: Spring break
03/25 Thu
No class: Spring break
03/30 Tue
Advanced topic: Test-time compute & Reasoning models
04/01 Thu
Advanced topic: Agents
04/06 Tue
MIDTERM (Scope: all material covered through the March 18 class)
04/08 Thu
MIDTERM REVIEW (will not be recorded)
04/13 Tue
Advanced topic: Vision-language models
04/15 Thu
Guest lecture (TBA)
04/20 Tue
Poster session
Project Checkpoint 2
04/22 Thu
Poster session
Project Checkpoint 2
04/27 Tue
No class: Office hours for project reports
04/29 Thu
No class: Office hours for project reports
Project Checkpoint 3 (final report) due by 05/06 (Thu)

Acknowledgement

The class materials, including lectures and assignments, are largely based on the following courses, whose instructors have generously made their materials publicly available. We are deeply grateful to them for sharing their work with the broader community: