• Credit Structure: 3-0-0-4-4

• This course provides an introduction to NLP, focusing on core algorithms and methods used to analyze and understand human language. Students will learn foundational concepts, tools, and techniques for processing text and speech, with applications in translation, summarization, and conversation.

Unit 1: Foundations of NLP

• • Introduction; Regular Expressions, Tokenization; Minimum Edit Distance; N-gram Language Models

Unit 2: Fundamental Algorithms of NLP

• • Naive Bayes & Text Classification; Sentiment Analysis

Unit 3: Neural Structures for NLP

• • Logistic Regression; Vector Semantics and Embeddings; Neural Networks; RNNs and LSTMs; Transformers; Large Language Models; Masked Language Models; Model Alignment, Prompting, and In-Context Learning

Unit 4: NLP Applications

• • Machine Translation; Question Answering, Information Retrieval, & RAG

Unit 5: Annotating Linguistic Structure

• • Sequence Labeling for Parts-of-Speech (POS) Tagging and Named Entity Recognition (NER); Context-Free Grammars and Constituency Parsing; Dependency Parsing; Information Extraction: Relations, Events, and Time; Semantic Role Labeling and Argument Structure; Coreference Resolution and Entity Linking; Discourse Coherence

Week 1:

• Course Introduction 

• Lecture 1: Introduction; Source: Chapter 1, Jurafsky & Martin

• Lecture 2: Regular Expressions, Tokenization; Source: Chapter 2, Jurafsky & Martin

• Self-Study 1: Basic text processing using RegExPal

Week 2:

• Lecture 3: Minimum Edit Distance; Source: Chapter 2, Jurafsky & Martin

• Lecture 4: N-gram Language Models; Source: Chapter 3, Jurafsky & Martin

• Self-Study 2: Basic text processing using NLTK and spaCy

Week 3:

• Lecture 5:  Naive Bayes & Text Classification; Source: Chapter 4, Jurafsky & Martin

• Lecture 6: Sentiment Analysis; Source: Chapter 4, Jurafsky & Martin

• Self-Study 3: Minimum Edit Distance

Week 4:

• Lecture 7: Logistic Regression; Source: Chapter 5, Jurafsky & Martin

• Lecture 8: Vector Semantics and Embeddings; Source: Chapter 6, Jurafsky & Martin

• Self-Study 4: Language Modelling

Week 5:

• Lecture 9: Neural Networks; Source: Chapter 7, Jurafsky & Martin

• Lecture 10: Neural Networks; Source: Chapter 7, Jurafsky & Martin

• Self-Study 5: Naive Bayes, Text Classification, and Sentiment Analysis

Week 6:

• Lecture 11: RNNs; Source: Chapter 8, Jurafsky & Martin

• Lecture 12: LSTMs; Source: Chapter 8, Jurafsky & Martin

• Self-Study 6: Logistic Regression

Week 7:

• Lecture 13: Extra Class

• Lecture 14: Extra Class

• Self-Study 7: Neural Networks

Week 8: 

• Midsem

Week 9:

• Lecture 15: Information Retrieval; Source: Chapter 14, Jurafsky & Martin

• Lecture 16: RAG; Source: Chapter 14, Jurafsky & Martin

• Self-Study 8: RNNs & LSTMs

Week 10:

• Lecture 17: Question Answering; Source: Chapter 14, Jurafsky & Martin

• Lecture 18: Machine Translation; Source: Chapter 13, Jurafsky & Martin

• Self-Study 9: Machine Translation

Week 11:

• Lecture 19: Sentiment Analysis II; Source: Slide 7, Jurafsky & Martin

• Lecture 20: Maximum Entropy Classification; Source: Slide 8, Jurafsky & Martin

• Self-Study 10: Named Entity Recognition (NER)

Week 12:

• Lecture 21: Information Extraction, Named Entity Recognition, & Relation Extraction; Source: Slide 9, Jurafsky & Martin

• Lecture 22: POS Tagging; Source: Slide 10, Jurafsky & Martin

• Self-Study 11: Parts-of-Speech (POS) Tagging

Week 13:

• Lecture 23: Statistical Natural Language Parsing; Source: Slide 11, Jurafsky & Martin

• Lecture 24: Probabilistic Parsing; Source: Slide 12, Jurafsky & Martin

• Self-Study 12: Context-Free Grammars, Constituency Parsing & Dependency Parsing

Week 14:

• Lecture 25: Lexicalized Parsing; Source: Slide 13, Jurafsky & Martin

• Lecture 26: Extra Class

• Self-Study 13: Information Extraction

Week 15:

• Lecture 27: Extra Class

• Lecture 28: Extra Class

• Self-Study 14: Discourse & Coherence

Week 16:

• Endsem

Extras:

• Lecture A: Transformers; Source: Chapter 9, Jurafsky & Martin

• Lecture B: Large Language Models; Source: Chapter 10, Jurafsky & Martin

• Lecture C: Masked Language Models; Source: Chapter 10, Jurafsky & Martin

• Lecture D: Model Alignment, Prompting & In-Context Learning; Source: Chapter 10, Jurafsky & Martin

"Speech and Language Processing" by Daniel Jurafsky and James H. Martin, Prentice Hall, 2024.

"Natural Language Understanding" by James Allen, Benjamin/Cummings Publishing Company, 1987.

"Foundations of Statistical Natural Language Processing" by Christopher D. Manning and Hinrich Schütze, MIT Press, 1999.

"A Primer on Neural Network Models for Natural Language Processing" by Yoav Goldberg, Online.

"Natural Language Processing with Python" by Steven Bird, Ewan Klein, Edward Loper, O'Reilly Media, Inc., 2009.

2 Theoretical Assignments (20%); Mid Sem (20%); End Sem (30%),  4 Practical Assignments (5%+5%+5%+15%)