SPPU · Third Year Information Technology · 2024 Pattern
Natural Language Processing
PEC-361D-IT · Elective II · Semester VI · 3 credits · CCE 30 + end-semester 70
One of the Elective II options.
Unit 1: Introduction to NLP
9 hoursApplications and characteristics of natural language; ambiguity; morphological, lexical, syntactic, semantic, discourse and pragmatic levels; challenges; corpora and corpus analysis.
Marks: 14 in the end-semester exam · CCE: Unit test (12 marks, Units 1 & 2)
- NLP and its applications
- Ambiguity in natural language
- Levels of language processing
- Corpora and corpus analysis
Unit 2: Lexical Analysis and Text Processing
9 hoursTokenisation, normalisation and stop words; stemming and lemmatisation; regular expressions; lexical resources and WordNet; part-of-speech tagging.
Marks: 14 in the end-semester exam · CCE: Unit test (12 marks, Units 1 & 2)
- Tokenisation and normalisation
- Stemming and lemmatisation
- Regular expressions for text
- WordNet and lexical resources
- Part-of-speech tagging
Unit 3: Syntactic and Semantic Processing
9 hoursCFGs, parsing and parse trees, syntactic ambiguity, dependency grammar; semantic representation, word-sense disambiguation and similarity; named-entity recognition and information extraction.
Marks: 14 in the end-semester exam · CCE: Assignments or case study (12 marks, Units 3 & 4)
- Parsing with context-free grammars
- Dependency grammar
- Word sense disambiguation
- Named entity recognition and information extraction
Unit 4: Statistical NLP
9 hoursN-gram language models; hidden Markov models; Bayesian approaches; vector-space models, bag of words and TF-IDF; word embeddings and neural language models.
Marks: 14 in the end-semester exam · CCE: Assignments or case study (12 marks, Units 3 & 4)
- N-gram language models
- Hidden Markov models
- Bag of words and TF-IDF
- Word embeddings
Unit 5: Applications and Emerging Trends
7 hoursMachine translation, information retrieval, question answering, summarisation and chatbots; multilingual NLP; transformers, LLMs and retrieval-augmented generation; bias and ethics.
Marks: 14 in the end-semester exam · CCE: Seminar, open-book test or quiz (6 marks, Unit 5)
- Machine translation and question answering
- Text summarisation and chatbots
- Transformers, LLMs and RAG
- Ethics and bias in NLP
Unit contents are summarised from the official SPPU syllabus . AiCanCode.org is not affiliated with Savitribai Phule Pune University.