RTMNU Final AI & ML syllabus

RTMNU · Final Year B.Tech Artificial Intelligence & Machine Learning · CBCS

Natural Language Engineering

BTAI&ML802T-5 · Elective V · Semester VIII · 3 credits · College 30 + university 70

One of the Elective V options.

  1. Unit 1: Overview and Language Modelling

    The origins and challenges of NLP, language and grammar, processing Indian languages, NLP applications and information retrieval; grammar-based and statistical language models.

    Examined in the 70-mark end-semester paper

    • Levels and challenges of NLP
    • Morphology of Indian languages
    • Grammar-based and statistical language models
    • N-gram language models
  2. Unit 2: Word-level and Syntactic Analysis

    Regular expressions, finite-state automata, morphological parsing, spelling-error detection and correction, word classes and part-of-speech tagging; context-free grammar, constituency, parsing and probabilistic parsing.

    Examined in the 70-mark end-semester paper

    • Regular expressions and finite automata
    • Morphology and finite-state transducers
    • Minimum edit distance
    • POS tagging
    • Context-free grammars
    • Probabilistic context-free grammars
  3. Unit 3: Extracting Relations from Text

    From word sequences to dependency paths; subsequence kernels and a dependency-path kernel for relation extraction, and their experimental evaluation.

    Examined in the 70-mark end-semester paper

    • Relation extraction and open information extraction
    • Kernel methods for relation extraction
  4. Unit 4: Evaluating Self-explanations in iSTART

    Word matching, latent semantic analysis and topic models; iSTART feedback systems and their evaluation.

    Examined in the 70-mark end-semester paper

    • Latent semantic indexing
    • Topic models
    • Automated feedback on self-explanations: iSTART
  5. Unit 5: Information Retrieval and Lexical Resources

    Design features of IR systems; classical, non-classical and alternative IR models and their evaluation; lexical resources — WordNet, FrameNet, stemmers, POS taggers and research corpora.

    Examined in the 70-mark end-semester paper

    • Information retrieval and extraction
    • Vector space model
    • WordNet
    • Indian language wordnets
    • FrameNet and lexical resources
    • Corpora and annotation

Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).