Textbooks:

An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models (Third Edition)

Daniel Jurafsky & James H. Martin

Draft of August 24, 2025

Hands-On Large Language Models

Jay Alammar & Maarten Grootendorst

Syllabus:

Part I – Foundations

Data Preparation & Tokenization, [slides]
N-Gram Language Models [slides]
Text Classification approaches [slides]
Intro to Neural Networks [slides]
Vector Semantics & Embeddings [slides]
Sequence Models: RNNs
Transformers
Text Clustering & Topic Modeling

Part II – Modern NLP

Prompting & In-Context Learning

Fine-Tuning Deep Dive
Retrieval-Augmented Generation & LLM Agents
Evaluation metrics
Deployment & Optimization

Part III – Speech Integration

Course Requirements

This course does not include formal homework assignments. Instead, each team will:

Select three research papers from the relevant literature,
- Read them thoroughly,
- Prepare a presentation for the class, and
Develop and implement novel ideas inspired by the literature, and present the results.
Prepare a formal 8-page paper (conference style) detailing your methods, experiments, and findings.

All implementation work will be done at the students’ own responsibility, including any GPU or computing costs required.

NOTE: Project topics should be chosen by students based on their interests. Choose your topics wisely—ambitious projects are encouraged, but make sure they are feasible within your time, skills, and available resources.

NOTE 2: In addition to the team project, a large part of your final grade will come from a comprehensive final exam. Homeworks will not be given, as they often fail to reflect true understanding due to widespread reliance on AI tools. The exam is intended to evaluate your independent understanding of the course material.

Page updated

Google Sites

Report abuse