Course

Unit 1

Introduction- History of NLP, Study of Human languages, ambiguity, Phases in natural language processing, applications. Textual sources and Formats. Linguistics resources- Introduction to the corpus, elements in the balanced corpus, (examples -TreeBank, PropBank, WordNet, VerbNet, etc.) Word Level analysis – Regular expressions, Morphological parsing, Types of Morphemes. Tokenization, N-grams, Stemming, Lemmatization, Spell checking. Management of linguistic data with NLTK.

Unit 2

Syntactic Analysis – Lexeme, phonemes, phrases and idioms, word order, agreement, tense, aspect and mood and agreement, Context Free Grammar, and spoken language syntax. Parsing- Unification, probabilistic parsing. Part of Speech tagging- Rule-based POS tagging, Stochastic POS tagging, Transformation-based tagging (TBL), Handling of unknown words, named entities, and multi-word expressions.

Semantics Analysis- Meaning representation, semantic analysis, lexical semantics, WordNet -WordNet similarity measures., Synsets and Hypernyms, Word Sense Disambiguation- Selectional restriction, machine learning approaches, dictionary-based approaches.

Unit 3

Discourse- Reference resolution, constraints on co-reference, an algorithm for pronoun resolution, text coherence, discourse structure. Information Retrieval-Types of an information retrieval model, Boolean Model, Vector space model-Word2Vec, BERT, Improving user queries. Machine Translation – EM algorithm – Discriminative learning – Deep representation learning – Generative learning.

Applications of NLP- Machine translation, Document Summarization, sentiment Analysis, ChatGPT4

Course Objectives

• This course is devoted to the study of phonological, morphological, and syntactic processing. These areas will be approached from both a linguistic and an algorithmic perspective.
• The course will focus on the computational properties of natural languages and the algorithms used to process them, as well as the match between grammar formalisms and the linguistic data that needs to be covered.

Course Outcomes

CO1: Understand the models, methods, and algorithms of statistical Natural Language Processing (NLP) for

common NLP tasks.

CO2: Understand mathematical and statistical models for NLP.

CO3: Understand linguistic phenomena and linguistic features relevant to each NLP task.

CO4: Develop probabilistic models for NLP.

CO5: Apply learning models to NLP tasks such as document summarization, machine translation, sentiment analysis and spell checking

CO-PO Mapping

Evaluation Pattern: 70:30

*CAT – Can be Quizzes, Assignments, and Reports

*CAL – Can be Lab Assessments, Project, and Report

**End Semester can be theory examination/ lab-based examination/ project presentation

Textbook(s)

Martin JH, Jurafsky D. “Speech and language processing: An introduction to natural language processing, computational linguistics, and speech recognition”. Pearson Publication, Second Edition; 2013.

 Reference(s)

James A. “Natural language Understanding”, Second Edition, Pearson Education; 2002.

Bharati A., Sangal R., Chaitanya V.“Natural language processing: a Paninian perspective”, PHI; 2000.

Tiwary U S, Siddiqui T. “Natural language processing and information retrieval”. Oxford University Press, Inc.; 2008.

Steven Bird, Ewan Klein, Edward Loper, “Natural Language Processing with Python – Analyzing Text with the Natural Language Toolkit” (O’Reilly 2009, website 2018)