DBATU · Final Year B.Tech Information Technology · Non-NEP
Natural Language Processing
BTITPE705E · Elective III · Semester VII · 3 credits · Continuous assessment 20 + mid-semester 20 + end-semester 60
One of the Elective III options.
Unit 1: Introduction and Morphology
NLP: definition, issues, applications and tools; the linguistic organisation of NLP; NLP versus PLP; inflectional and derivational morphology; parsing with finite-state transducers.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- NLP and its applications
- Levels of language processing
- NLP tools and linguistic organisation
- Inflectional and derivational morphology
- Finite-state morphology
Unit 2: Text Processing and N-gram Models
Basic text processing; simple n-grams and counting words in corpora; add-one, Witten–Bell and Good–Turing smoothing; n-grams for spelling and pronunciation.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Tokenisation and normalisation
- N-gram language models
- Smoothing: add-one, Witten-Bell and Good-Turing
- Spelling error detection and correction
Unit 3: Part-of-speech Tagging
Tagsets; HMM taggers and their algorithm; rule-based and stochastic tagging; transformation-based tagging; MaxEnt and CRF models for sequential tagging.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Part-of-speech tagging
- Hidden Markov models
- Transformation-based tagging
- MaxEnt and CRF sequence models
Unit 4: Parsing and Semantics
CFGs and parsing techniques; constituency and dependency parsing; distributional and lexical semantics, lexemes and WordNet; metaphor and metonymy; selectional-restriction, machine-learning and dictionary-based word sense disambiguation.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Parsing with context-free grammars
- Dependency grammar
- Distributional and lexical semantics
- WordNet and lexical resources
- Metaphor and metonymy
- Word sense disambiguation
Unit 5: Applications
Topic models; entity linking; information extraction; text summarisation; text classification; sentiment analysis and opinion mining.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Topic models
- Entity linking
- Named entity recognition and information extraction
- Text summarisation and chatbots
- Text classification
- Sentiment analysis and opinion mining
Unit contents are summarised from the official DBATU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Technological University (DBATU).