SGBAU · Third Year B.E. Artificial Intelligence and Data Science · NEP 2020
Natural Language Processing
6AD234PE1 · Elective II · Semester VI · 3 credits · IE 40 + ESE 60
One of the Elective II options.
Unit 1: Overview and Morphology
6 hoursNLP, its models and algorithms; regular expressions and finite-state automata; morphology — inflectional and derivational — and finite-state morphological parsing.
Examined in the 60-mark end-semester paper
- Levels and challenges of NLP
- Regular expressions and finite automata
- Morphology and finite-state transducers
- Stemming and lemmatisation
Unit 2: Word-Level Analysis
6 hoursLanguage models and simple n-grams, estimation and smoothing, evaluating language models; part-of-speech tagging and sequence labelling, lexical syntax, hidden Markov models and maximum-entropy models.
Examined in the 60-mark end-semester paper
- N-gram language models
- Perplexity and smoothing
- POS tagging
- Hidden Markov models
- Maximum entropy models and CRFs
Unit 3: Syntactic Analysis
6 hoursContext-free grammars and grammar rules for English, treebanks, normal forms, dependency grammar, syntactic parsing and ambiguity, and probabilistic and lexicalised probabilistic CFGs.
Examined in the 60-mark end-semester paper
- Context-free grammars
- Corpora and annotation
- Dependency parsing
- Probabilistic context-free grammars
- Earley and CYK parsing
Unit 4: Semantic Analysis
6 hoursRepresenting meaning and the meaning structures of language, first-order predicate calculus, syntax-driven semantic analysis and semantic attachments, robust semantic analysis, lexemes and their senses, and word-sense disambiguation.
Examined in the 60-mark end-semester paper
- Semantic roles
- WordNet
- Word sense disambiguation
Unit 5: Learning to Classify Text
6 hoursSupervised classification and its examples, evaluating classifiers, decision trees, naive Bayes classifiers and modelling linguistic patterns.
Examined in the 60-mark end-semester paper
- Naive Bayes text classification
- Logistic regression for text classification
- Decision tree learning and overfitting
- Classification metrics
Unit 6: Information Extraction from Text
6 hoursInformation extraction, chunking and its evaluation, recursion in linguistic structure, named-entity recognition and relation extraction.
Examined in the 60-mark end-semester paper
- Shallow parsing
- Named entity recognition
- Relation extraction and open information extraction
- Information retrieval and extraction
Unit contents are summarised from the official SGBAU syllabus . AiCanCode.org is not affiliated with Sant Gadge Baba Amravati University (SGBAU).