Natural Language Processing For MU Sem 7 Computer Engineering Course Code : CSDC7013) Academic Year 2022-2023  (Paperback, Prof. R. M. Baphana, Dr. Tatwadarshi P. Nagarhalli)

Module Detailed Content Hours 1 1.1 Introduction to NLP 03 Origin & History of NLP; Language, Knowledge and Grammar in language processing; Stages in NLP;Ambiguities and its types in English and Indian Regional Llanguages; Challenges of NLP;Applications of NLP. 1.2 Self-Learning topics : Variety types of tools for regional languages preprocessing and other functionalities (Refer Chapter 1)2.0 2.1 Word Level Analysis 09 Basic Terms: Tokenization, Stemming, Lemmatization; Survey of English Morphology, Inflectional Morphology, Derivational Morphology; Regular expression with types; Morphological Models: Dictionary lookup, finite state morphology; Morphological parsing with FST (Finite State Transducer);Lexicon free FST Porter Stemmer algorithm; Grams and its variation: Bigram, Trigram; Simple (Unsmoothed) N-grams; N-gram Sensitivity to the Training Corpus; Unknown Words: Open. versus closed vocabulary tasks; Evaluating N-grams: Perplexity; Smoothing: Laplace Smoothing, Good-Turing Discounting; 2.2 Self-Learning topics: Noisy channel models, various edit distance, Advance Issues in Language Modelling. (Refer Chapter 2) 3.0 3.1 Syntax analysis 10 Part-Of-Speech tagging(POS); Tag set for English (Upenn Treebank); Difficulties /Challenges in POS tagging; Rule-based, Stochastic and Transformation-based tagging; Generative Model: Hidden Markov Model (HMM Viterbi) for POS tagging; Issues in HMM POS tagging; Discriminative Model: Maximum Entropy model, Conditional random Field (CRF);Parsers: Top down and Bottom up; Modelling constituency; Bottom Up Parser: CYK, PCFG (Probabilistic Context Free Grammar), Shift Reduce Parser; Top Down Parser: Early Parser, Predictive Parser 3.2 Self-Learning topics: Evaluating parsers, Parsers based language modelling, Regional languages POS tree banks. (Refer Chapter 3) 4.0 4.1 Semantic Analysis 07 Introduction, meaning representation; Lexical Semantics; Corpus study; Study of Various language dictionaries like WorldNet, Babelnet; Relations among lexemes & their senses –Homonymy, Polysemy, Synonymy, Hyponymy; Semantic Ambiguity; Word Sense Disambiguation (WSD); Knowledge based approach(Lesk‘s Algorithm), Supervised (Naïve Bayes, Decision List),Introduction to Semi-supervised method (Yarowsky) Unsupervised (Hyperlex) 4.2 Self-Learning topics: Dictionaries for regional languages, Distributional Semantics, Topic Models. (Refer Chapter 4)5.0 5.1 Pragmatic & Discourse Processing 05 Discourse: Reference Resolution, Reference Phenomena, Syntactic & Semantic constraint on coherence; Anaphora Resolution using Hobbs and Cantering Algorithm. 5.2 Self-Learning topics: Discourse segmentation, Conference resolution. (Refer Chapter 5) 6.0 6.1 Applications of NLP 05 Case studies on (preferable in regional language) : Machine translation; Text Summarization; Sentiment analysis; Information retrieval; Question Answering system. 6.2 Self-Learning topics : Applications based on Deep Neural Network with NLP such as LSTM network, Recurrent Neural network etc. (Refer Chapter 6)