DBATU · Third Year B.Tech Artificial Intelligence & Allied · NEP 2020
Natural Language Processing
26AFAIPC602 · Semester VI · 3 credits · Continuous assessment 20 + mid-semester 20 + end-semester 60
Unit 1: Lexical Analysis
5 hoursRegular expressions and automata for string matching; words and word forms; morphology and its diversity in Indian languages, paradigms, finite-state transducers and automatic morphology learning; parts of speech, n-gram models and HMMs.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Regular expressions and finite automata
- Morphology and finite-state transducers
- Morphology of Indian languages
- POS tagging
- N-gram language models
- Hidden Markov models
Unit 2: Speech Processing
5 hoursThe biology of speech, place and manner of articulation; word-boundary detection and argmax computations; HMMs and speech recognition; rule-based and concatenative text-to-speech synthesis.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Speech production and articulation
- HMM-based speech recognition
- Text-to-speech synthesis
Unit 3: Parsing
4 hoursTheories and algorithms of parsing: Earley and CYK; probabilistic parsing; attachment and structural ambiguity; shallow and dependency parsing; named entity recognition; maximum entropy models and conditional random fields.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Earley and CYK parsing
- Probabilistic context-free grammars
- Shallow parsing
- Dependency parsing
- Named entity recognition
- Maximum entropy models and CRFs
Unit 4: Lexical Knowledge Networks
5 hoursWordNet theory, Indian language wordnets and multilingual dictionaries; semantic roles; word sense disambiguation and multilingualism; metaphors; coreference and anaphora resolution.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- WordNet
- Indian language wordnets
- Semantic roles
- Word sense disambiguation
- Coreference and anaphora resolution
Unit 5: Applications
5 hoursSentiment analysis, textual entailment, machine translation, question answering, information retrieval and extraction, and cross-lingual information retrieval.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Sentiment analysis
- Machine translation
- Question answering systems
- Information retrieval and extraction
- Textual entailment and cross-lingual retrieval
Unit contents are summarised from the official DBATU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Technological University (DBATU).