CS 5134/6034: Natural Language Processing

This course is a basic introduction to natural language processing (NLP). We will study the fundamentals of different subfields within NLP, and the theoretical concepts and algorithms used for typical NLP problems. Topics include text classification, language modeling, sequence tagging, word embeddings, neural networks, transformers, and large language models. By the end of the course, you will understand the research questions and methods in different areas of NLP, and you will be able to build NLP systems for new problems.

Assignments (3): 30%

Midterm Exam (in-class): 30%

Project: 40%

Bonus: 5% (class attendance)

Late Policy: 24 hour grace period with 10% penalty. No points after 24 hours.
Regrading Policy: Regrade requests must be made within two weeks of the score being posted on Canvas.
Electronic Submission: All assignments and project reports need to be submitted electronically via Canvas and Gradescope.

This course assumes a good background in basic probability, statistics, linear algebra, and good programming skills in Python3. Prior knowledge of machine learning is helpful, but not required. The class is mainly for advanced undergraduates and graduate students in computer science, but we welcome other interested students with the necessary background and programming skills.

Week	Date	Topic	Reading	Assignment
1	08/25	Introduction to NLP	Ch. 1
	08/27	Morphology	Ch. 2
2	09/01	N-gram Language Models	Ch. 3	a1 out
	09/03	N-gram Language Models contd.	Ch. 3
3	09/08	Naive Bayes	App. B
	09/10	Logistic Regression	Ch. 4
4	09/15	Part-of-Speech Tagging	Ch. 18
	09/17	HMM and Viterbi	Ch. 18 & App. A
5	09/22	Sequence Labeling	Ch. 18	a1 due, a2 out
	09/24	Lexical Semantics	App. I
6	09/29	Distributional Representations	Ch. 5 & App. J
	10/01	Word Embeddings	Ch. 5
7	10/06	Neural Networks for NLP	Ch. 6	proposal due
	10/08	RNNs	Ch. 14
8	10/13	Machine Translation and Seq2Seq	Ch. 13	a2 due
	10/15	Attention	Ch. 7
9	10/20	Transformers	Ch. 7	a3 out
	10/22	Transformers contd.	Ch. 7
10	10/27	Midterm Exam
	10/29	Pre-train and Fine-tune	Ch. 7 & 9
11	11/03	NO CLASS (Reading Day)
	11/05	Post-training	Ch. 8	intermediate report due
12	11/10	Prompting	Ch. 1
	11/12	Reasoning		a3 due
13	11/17	Agents and Tool Use
	11/19	Project Presentations
14	11/24	Project Presentations
	11/26	NO CLASS (Thanksgiving)
15	12/01	Project Presentations
	12/03	Project Presentations		slides & final report due

Every team works on one SemEval-2027 shared task. Training data is scheduled for 1 September 2026. Task pages and data: https://semeval.github.io/SemEval2027/tasks. See the project handout on Canvas for reports and presentation rules.