Course Details
Subject {L-T-P / C} : CS6314 : Natural Language Processing { 3-0-0 / 3}
Subject Nature : Theory
Coordinator : Dr. Tapas Kumar Mishra
Syllabus
Introduction, Mathematical Preliminaries [2hrs]
Basic Text Processing, Edit distance [2hrs]
Linear Text Classification (NB,LR) [4hrs]
Word Embeddings [3hrs]
Language models, spelling correction [3hrs]
Neural Networks and Neural Language Models [3hrs]
Deep Learning Architectures for Sequence Processing [3hrs]
Sequence labelling POS tagging, NER, Tokenization [3hrs]
Parsing [3hrs]
Machine Translation [4hrs]
Semantics [4hrs]
Reference resolution, Discourse (Entity Linking) [2hrs]
Information/Relation Extraction [1hrs]
Question Answering [1hrs]
Summarization [1hrs]
Dialogue Systems [1hrs]
Sentiment Analysis [2hrs]
Course Objectives
- to understand the basics of language processing
- to learn about language models, sequence labelling tasks
- to learn about parsing, machine translation systems
- to learn about Q/A systems, Summarization, Chatbots
Course Outcomes
Students will learning the following: <br />1. How a language model works <br />2. How a POS tagging system, NER systems works <br />3. How to design a Parser for a given language <br />4. How to design a statistical as well as neural machine translation model <br />5. How a Q/A system and Chatbot works <br />6. How a summarization model works
Essential Reading
- (Daniel Jurafsky and James Martin, Speech and Language Processing, Prentice-Hall , Second Edition, 2008 <br />ISBN: 0131873210
- Christopher Manning and Hinrich Schutze, Foundations of Statistical Natural Language Processing, MIT Press , 1999
Supplementary Reading
- Deepti Chopra, Jacob Perkins, and Nitin Hardeniya, Natural Language Processing: Python and NLTK, packt
- Dipanjan Sarkar, Text Analytics with Python: A Practical Real-World Approach to Gaining Actionable Insights from Your Data, Apress