Mumbai University BE EXTC syllabus

Mumbai University · Final Year Electronics and Telecommunication Engineering · Rev-2019 'C' Scheme

Natural Language Processing

ECCDLO8012 · Department Optional Course 5 · Semester VIII · 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. Each module's share of the paper follows its lecture hours.

One of the Department Optional Course 5 options.

All notes for this subject
  1. Module 1: Introduction to NLP

    6 hours

    Need for NLP; generic NLP systems; levels of NLP; stages of building an NLP system; challenges and ambiguities.

    Examined in the 80-mark end-semester paper (about 15% of it, by lecture hours); the class tests cover what has been taught by then

    • Need and levels of NLP
    • Stages and ambiguities in NLP
  2. Module 2: Mathematical and Linguistic Preliminaries

    6 hours

    Probability, Bayes' rule, random variables and distributions; English grammar, parts of speech and phrase structure.

    Examined in the 80-mark end-semester paper (about 15% of it, by lecture hours); the class tests cover what has been taught by then

    • Probability for NLP
    • English grammar and phrase structure
  3. Module 3: Word-level Analysis

    6 hours

    Tokenisation, segmentation and lemmatisation; edit distance; collocations; the Porter stemmer; n-gram models; derivational and inflectional morphology.

    Examined in the 80-mark end-semester paper (about 15% of it, by lecture hours); the class tests cover what has been taught by then

    • Tokenisation, segmentation and lemmatisation
    • Edit distance
    • Porter stemmer
    • N-gram language models
    • Morphological analysis
  4. Module 4: Syntax Analysis

    8 hours

    The Penn Treebank tagset; POS tagging; Markov processes and HMMs; HMM tagging with Viterbi.

    Examined in the 80-mark end-semester paper (about 21% of it, by lecture hours); the class tests cover what has been taught by then

    • Penn Treebank tagset
    • Hidden Markov models
    • POS tagging with HMMs and Viterbi
  5. Module 5: Semantic Analysis

    8 hours

    Lexical semantics and sense relations; WordNet, glosses and synsets; cosine distance between documents; word sense disambiguation.

    Examined in the 80-mark end-semester paper (about 21% of it, by lecture hours); the class tests cover what has been taught by then

    • Lexical semantics and word relations
    • WordNet
    • Cosine similarity between documents
    • Word sense disambiguation
  6. Module 6: Pragmatics and Applications

    5 hours

    Reference resolution and discourse models; categorisation, summarisation, sentiment analysis, NER, translation, IR and question answering.

    Examined in the 80-mark end-semester paper (about 13% of it, by lecture hours); the class tests cover what has been taught by then

    • Reference resolution
    • NLP applications: summarisation, sentiment and translation

Module contents are summarised from the official Mumbai University syllabus . AiCanCode.org is not affiliated with the University of Mumbai.