Natural Language Processing syllabus
PEC-361D-IT · Third Year Information Technology, SPPU 2024 pattern. Every unit, the marks scheme, course outcomes and books, copied from the official syllabus PDF.
Unit-wise syllabus
Introduction To Natural Language Processing
9 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Introduction to Natural Language Processing, applications of NLP, characteristics of natural language, ambiguity in natural language, levels of language processing (morphological, lexical, syntactic, semantic, discourse and pragmatic processing), challenges in NLP, corpus and corpus analysis Case Studies: Intelligent Virtual Assistants and Conversational Systems.
Preserved official unit paragraph
Introduction to Natural Language Processing, applications of NLP, characteristics of natural language, ambiguity in natural language, levels of language processing (morphological, lexical, syntactic, semantic, discourse and pragmatic processing), challenges in NLP, corpus and corpus analysis Case Studies: Intelligent Virtual Assistants and Conversational Systems.
Lexical Analysis And Text Processing
9 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Text preprocessing, tokenization, normalization, stop-word removal, stemming, lemmatization, regular expressions, lexical analysis, lexical resources, dictionaries and thesauri, WordNet, part-ofspeech tagging and applications.
- Case Studies: Document Classification and Text Processing Systems
Preserved official unit paragraph
Text preprocessing, tokenization, normalization, stop-word removal, stemming, lemmatization, regular expressions, lexical analysis, lexical resources, dictionaries and thesauri, WordNet, part-ofspeech tagging and applications. Case Studies: Document Classification and Text Processing Systems
Syntactic And Semantic Processing
9 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Context-Free Grammar (CFG), parsing techniques, parse trees, syntactic ambiguity, dependency grammar, semantic representation, word sense disambiguation, semantic similarity, named entity recognition, information extraction techniques.
- Case Studies: Information Extraction from Unstructured Text
Preserved official unit paragraph
Context-Free Grammar (CFG), parsing techniques, parse trees, syntactic ambiguity, dependency grammar, semantic representation, word sense disambiguation, semantic similarity, named entity recognition, information extraction techniques. Case Studies: Information Extraction from Unstructured Text
Statistical Natural Language Processing
9 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Probabilistic approaches to NLP, N-gram language models, language modeling, Hidden Markov Models, Bayesian approaches, vector space models, Bag-of-Words representation, TF-IDF weighting, word embeddings, introduction to neural language models.
- Case Studies: Sentiment Analysis and Opinion Mining.
Preserved official unit paragraph
Probabilistic approaches to NLP, N-gram language models, language modeling, Hidden Markov Models, Bayesian approaches, vector space models, Bag-of-Words representation, TF-IDF weighting, word embeddings, introduction to neural language models. Case Studies: Sentiment Analysis and Opinion Mining.
NLP Applications And Emerging Trends
7 hoursDerived reading outline. Source text split at semicolons, line breaks and sentence boundaries, not an official topic hierarchy.
- Machine translation, information retrieval, question answering systems, text summarization, chatbots and conversational AI, multilingual NLP, transformer architecture (overview), Large Language Models and Retrieval-Augmented Generation (overview), ethical issues in NLP, bias and fairness, future trends and research challenges.
- Case Studies: Machine Translation Systems, Conversational AI Platforms
Preserved official unit paragraph
Machine translation, information retrieval, question answering systems, text summarization, chatbots and conversational AI, multilingual NLP, transformer architecture (overview), Large Language Models and Retrieval-Augmented Generation (overview), ethical issues in NLP, bias and fairness, future trends and research challenges. Case Studies: Machine Translation Systems, Conversational AI Platforms
Marks and credits
| Head | Marks | Credit |
|---|---|---|
| CCE (continuous comprehensive evaluation) | 30 | 3 |
| End-semester exam | 70 |
Prerequisite: Operating System, Data Science.
Course outcomes
- CO1Understand the concepts, challenges and applications of Natural Language Processing.
- CO2Apply text preprocessing and lexical analysis techniques to textual data.
- CO3Analyze syntactic and semantic structures in natural language.
- CO4Analyze statistical approaches and language models used in NLP systems.
- CO5Evaluate NLP applications and recent developments in language technologies.
Books
Text books
- Natural Language Processing and Information Retrieval by Tanveer Siddiqui, U. S. Tiwary Publisher: Oxford University Press
- Speech and Language Processing by Daniel Jurafsky, James H. Martin
Reference books
- Natural Language Processing with Python by Steven Bird, Ewan Klein, Edward Loper Publisher: O'Reilly Media
- Foundations of Statistical Natural Language Processing by Christopher Manning, Hinrich Schütze
- Natural Language Understanding by James Allen
FAQ
How many units are in Natural Language Processing?
Natural Language Processing (PEC-361D-IT) has 5 units: Unit I Introduction To Natural Language Processing (9 h); Unit II Lexical Analysis And Text Processing (9 h); Unit III Syntactic And Semantic Processing (9 h); Unit IV Statistical Natural Language Processing (9 h); Unit V NLP Applications And Emerging Trends (7 h).
What is the marks scheme for Natural Language Processing?
The official Information Technology 2024 pattern syllabus lists continuous comprehensive evaluation (CCE) for 30 marks and the end-semester exam for 70 marks, for 3 credits.
What should I know before Natural Language Processing?
Prerequisite listed in the syllabus: Operating System, Data Science.