CAP 4641 Natural Language Processing

Course Information

Course Title: CAP 4641 Natural Language Processing

Semester: Fall 2026

Lectures: Mondays 5:10pm - 8:10pm at LIT 0109

Office Hours: Mondays 9:30am - 10:30am, location refer to syllabus

Course Description

A comprehensive introduction to Natural Language Processing (NLP) and Large Language Models (LLMs), a foundational technology behind recent breakthroughs in Artificial Intelligence (AI). Fundamental knowledge in NLP and LLMs, including machine learning models for text classification, word embedding, LLM tokenization, LLM model architectures, recurrent neural network-based language models, sequence-to-sequence language models, attention mechanism, transformer-based language models, as well as pre-training, fine-tuning, decoding, and post-training techniques in LLMs are introduced.

Grading

• Assignments: 50% (10% + 10% + 15% + 15%)

• Final Exam: 50% (Dec 9th 2026 12:30pm-2:30pm)

Course Schedule (tentative)

Week #                                           Topics

Week 1                                                  Lectures Introduction and Overview

                                                               Text Classification, Naive Bayes, Logistic Regression

Week 2                                                  Sequence Language Model, Hidden Markov Models, Viberti Decoding

                                                               Maximum Entropy Markov Models, Conditional Random Fields

Week 3                                                  Word Embedding, Word2vec Algorithm

                                                                Document Embedding, Document Similarity, Document Retrieval

Week 4                                                  N-gram Language Model

                                                               LLMs Tokenization Algorithms, Byte-Pair Encoding, WordPiece, Unigram Tokenizer (optional)

Week 5                                                  Neural Architectures for Language Model, 

                                                               Feedforward Neural Language Model

Week 6                                                  Recurrent Neural Network for Language Model, Long Short-Term Memory Model

                                                               Sequence-to-Sequence Language Model

Week 7                                                  Attention Mechanism, Self-Attention, Multi-head Attention

                                                               Transformer-based Language Model

Week 8                                                  Pre-Training of Large Language Models

                                                               Encoder Language Model, Encoder-Decoder Language Model, Decoder-only Language Model

Week 9                                                  Fine-Tuning of Large Language Models

                                                               Parameter-Efficient Fine-Tuning of Large Language Models

Week 10                                                Inference and Generation of Large Language Models, 

                                                               LLMs Decoding Strategies, Controllable Text Generation, Generation Evaluation

Week 11                                                Post-Training of Large Language Models

                                                               In-context Learning, Instruction Tuning, Preference Alignment

Week 12                                                Reinforcement Learning in Large Language Models, Proximal Policy Optimization (PPO), 

                                                               Direct Preference Optimization (DPO), Group Relative Policy Optimization (GRPO)