Mumbai University · Final Year Computer Engineering · Rev-2019 'C' Scheme
Natural Language Processing
CSDC7013 · Department Optional Course 3 · Semester VII · 3 credits · Internal tests 20 (average of two) + end-semester 80
End-semester paper (3 hours): Six questions of 20 marks; Q1 is compulsory and you answer four.
One of the Department Optional Course 3 options.
Module 1: Introduction to NLP
3 hoursHistory of NLP; language, knowledge and grammar; stages of NLP; ambiguity in English and Indian languages; challenges and applications.
Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then
- Natural language processing and its challenges
- Stages of NLP
Module 2: Word-level Analysis
9 hoursTokenisation, stemming and lemmatisation; inflectional and derivational morphology; regular expressions; dictionary lookup and finite-state morphology; FST parsing and the Porter stemmer; n-grams, perplexity and smoothing with Laplace and Good–Turing.
Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then
- Tokenisation, stemming and lemmatisation
- Morphological analysis and finite-state transducers
- Porter stemmer
- N-gram language models and smoothing
- Evaluating language models
Module 3: Syntax Analysis
10 hoursPOS tagging and the Penn Treebank; rule-based, stochastic and transformation-based tagging; HMM with Viterbi; maximum entropy and CRF; top-down and bottom-up parsers; CYK, PCFG and shift-reduce; Earley and predictive parsers.
Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then
- Part-of-speech tagging
- HMM tagging and the Viterbi algorithm
- Maximum entropy and CRF taggers
- Syntactic parsing and probabilistic CFGs
- CYK and Earley parsers
Module 4: Semantic Analysis
7 hoursMeaning representation; lexical semantics; WordNet and BabelNet; homonymy, polysemy, synonymy and hyponymy; WSD with Lesk, naive Bayes, decision lists, Yarowsky and HyperLex.
Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then
- Lexical semantics and WordNet
- Word sense disambiguation
- Lesk and Walker's algorithms
Module 5: Pragmatics and Discourse
5 hoursReference resolution; constraints on coherence; anaphora resolution with Hobbs and centering algorithms.
Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then
- Coreference resolution
- Anaphora resolution: Hobbs and centering algorithms
Module 6: Applications of NLP
5 hoursMachine translation; text summarisation; sentiment analysis; information retrieval; question answering.
Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then
- Machine translation
- Text summarisation
- Sentiment analysis
- Question answering and textual entailment
Module contents are summarised from the official Mumbai University syllabus . AiCanCode.org is not affiliated with the University of Mumbai.