Course Code: Course Title Credit
CSDO7011 Natural Language Processing 3
Prerequisite: Artificial Intelligence and Machine Learning, Basic knowledge of Python
Course Objectives:
1 To understand natural language processing and to learn how to apply basic algorithms in this field
2 To get acquainted with the basic concepts and algorithmic description of the main language levels:
morphology, syntax, semantics, and pragmatics
3 To design and implement various language models and POS tagging techniques
4 To design and learn NLP applications such as Information Extraction, Question answering
5 To design and implement applications based on natural language processing
Course Outcomes:
1 To have a broad understanding of the field of natural language processing
2 To design language model for word level analysis for text processing
3 To design various POS tagging techniques
4 To design, implement and test algorithms for semantic analysis
5 To develop basic understanding of Pragmatics and to formulate the discourse segmentation and
anaphora resolution
6 To apply NLP techniques to design real world NLP applications
Module Content Hrs
1 Introduction 4
1.1 Origin & History of NLP, The need of NLP, Generic NLP System, Levels
of NLP, Knowledge in Language Processing, Ambiguity in Natural
Language, Challenges of NLP, Applications of NLP.
2 Word Level Analysis 8
2.1 Tokenization, Stemming, Segmentation, Lemmatization, Edit Distance,
Collocations, Finite Automata, Finite State Transducers (FST), Porter
Stemmer, Morphological Analysis, Derivational and Reflectional
Morphology, Regular expression with types.
2.2 N –Grams, Unigrams/Bigrams Language Models, Corpora, Computing the
Probability of Word Sequence, Training and Testing.
3 Syntax analysis 8
3.1 Part-Of-Speech Tagging (POS) - Open and Closed Words. Tag Set for
English (Penn Treebank), Rule Based POS Tagging, Transformation Based
Tagging, Stochastic POS Tagging and Issues –Multiple Tags & Words,
Unknown Words.
3.2 Introduction to CFG, Hidden Markov Model (HMM), Maximum Entropy,
And Conditional Random Field (CRF).
4 Semantic Analysis 8
4.1 Introduction, meaning representation; Lexical Semantics; Corpus study;
Study of Various language dictionaries like WordNet, Babelnet; Relations
among lexemes & their senses –Homonymy, Polysemy, Synonymy,
Hyponymy; Semantic Ambiguity
4.2 Word Sense Disambiguation (WSD); Knowledge based approach (Lesk‘s
Algorithm), Supervised (Naïve Bayes, Decision List), Introduction to
Semi-supervised method (Yarowsky), Unsupervised (Hyperlex)
5 Pragmatic & Discourse Processing 6
5.1 Discourse: Reference Resolution, Reference Phenomena, Syntactic &
Semantic constraint on coherence; Anaphora Resolution using Hobbs and
Cantering Algorithm
6 Applications (preferably for Indian regional languages) 5
6.1 Machine Translation, Information Retrieval, Question Answers System,
Categorization, Summarization, Sentiment Analysis, Named Entity
Recognition.
6.2 Linguistic Modeling – Neurolinguistics Models- Psycholinguistic Models –
Functional Models of Language – Research Linguistic Models- Common
Features of Modern Models of Language.
Textbooks:
1 Daniel Jurafsky, James H. and Martin, Speech and Language Processing, Second Edition,
Prentice Hall, 2008.
2 Christopher D.Manning and HinrichSchutze, Foundations of Statistical Natural Language
Processing, MIT Press, 1999.
References:
1 Siddiqui and Tiwary U.S., Natural Language Processing and Information Retrieval, Oxford
University Press, 2008.
2 Daniel M Bikel and ImedZitouni ― Multilingual natural language processing applications: from
theory to practice, IBM Press, 2013.
3 Nitin Indurkhya and Fred J. Damerau, ―Handbook of Natural Language Processing, Second
Edition, Chapman and Hall/CRC Press, 2010.
Assessment:
Internal Assessment:
Assessment consists of two class tests of 20 marks each. The first class test is to be conducted when
approx. 40% syllabus is completed and second class test when additional 40% syllabus is completed.
Duration of each test shall be one hour.
End Semester Theory Examination:
1 Question paper will comprise of total six questions.
2 All question carries equal marks
3 Questions will be mixed in nature (for example supposed Q.2 has part (a) from module 3 then
part (b) will be from any module other than module 3)
4 Only Four question need to be solved
5 In question paper weightage of each module will be proportional to number of respective lecture
hours as mention in the syllabus
Useful Links
1 https://onlinecourses.nptel.ac.in/noc21_cs102/preview
2 https://onlinecourses.nptel.ac.in/noc20_cs87/preview
3 https://nptel.ac.in/courses/106105158
