Course

Syllabus

WORDS: Introduction – Mathematical Foundations Linguistic Essentials – Regular Expressions, Text Normalization, Edit Distance- Finite State Transducers

CLASSICAL NLP & SEQUENCE MODELING: Language Modeling with N-grams – Naive Bayes Classification and Sentiment – Neural Nets and Neural Language Models – Hidden Markov Models – Part-of-Speech Tagging.

SYNTAX: Formal Grammars of English – Syntactic Parsing Ambiguity CockeKasami Younger (CKY) algorithm-PCFG Inside and Outside probabilities – Dependency Grammar Transition based parsing-MST based Dependency parsing.

SEMANTICS: Vector Semantics – Semantics with Dense Vectors – Word Senses: WSD and WordNet – Lexicons for Sentiment and Affect Extraction – Representation of Sentence Meaning – Computational Semantics – Information Extraction Named Entity Recognition – Semantic Role Labeling and Argument Structure – Coreference Resolution and Entity Linking.

PRAGMATICS AND APPLICATIONS: Discourse Coherence Neural Sequence modeling: RNN, LSTM Text Summarization – Topic Modelling – Question Answering.

NATURAL LANGUAGE GENERATION: Architecture of NLG Systems- Generation Tasks and Representations Application of NLG. Machine Translation: Language similarities and differences – The transfer metaphor Direct Translation Statistical translation – Translation involving Indian Languages.

Text Books / References

Text Books

1. Daniel Jurafsky and James H. Martin, “Speech and Language Processing “, Prentice –hall, Inc., 2017.
2. Christopher D. Manning, Hinrich Schutze, “Foundations of Statistical Natural Language Processing”, The MIT Press, 2018.

References

1. Yoav Goldberg, “Neural Network Methods for Natural Language Processing”, Synthesis Lectures on Human Language Technologies, April 2017.
2. Steven Bird, Ewan Klein, and Edward Loper, “Natural Language Processing with Python – Analyzing Text with the Natural Language Toolkit”, O,Reilly. 2019
3. Li Deng and Yang Liu, “Deep Learning in Natural Language Processing”, Springer, Germany. 2018.
4. Dipanjan Sarkar, “Text Analytics with Python – A Practitioner’s Guide to Natural Language Processing, Apress, 2019
5. Jalaj Thanaki, “Python Natural Language Processing – Advanced machine learning and deep learning techniques for natural language processing, Packt Publisher, 2017.

Natural language processing (NLP) or computational linguistics is one of the most important technologies of the information age. Applications of NLP are everywhere because people communicate almost everything in natural language: web search, advertising, emails, customer service, language translation, virtual agents, medical reports, politics, etc. In the 2010s, deep learning (or neural network) approaches obtained very high performance across many different NLP tasks, using single end-to-end neural models that did not require traditional, task-specific feature engineering. In the 2020s amazing further progress was made through the scaling of Large Language Models, such as Chat GPT. In this course, students will gain a thorough introduction to both the basics of Deep Learning for NLP and the latest cutting-edge research on Large Language Models (LLMs).

Course Outcomes: After successful completion of the course, students will be able to

1. CO1: Understand themathematical and linguistic foundations of NLP, including regular expressions, finite state transducers, language modeling, neural language models, and probabilistic models such as Hidden Markov Models and Naive Bayes.
2. CO2: Analyse and implement syntactic parsing techniques using formal grammars, CKY algorithm, probabilistic context-free grammars (PCFG), and dependency parsing methods.
3. CO3: Apply semantic processing techniques including vector semantics, word sense disambiguation, sentiment analysis, information extraction, named entity recognition, semantic role labeling, and coreference resolution.
4. CO4: Develop NLP applications using neural sequence models (RNN, LSTM) for tasks such as text summarization, topic modeling, question answering, and discourse analysis.
5. CO5: Design natural language generation and machine translation systems, analyzing linguistic similarities and differences, and applying statistical and transfer-based translation approaches.

CO-PO Mapping: