Subject Natural Language Processing Subject Code: TM3 403 (2)
Name:
Course Name: Master of Computer Applications (MCA)
1 Contact Hours: 45 L 3 T 0 P 0
2 Examination Duration(Hrs): Theory 0 3 Practical 0 0
3 Relative Weightage: CWE: 25 MTE: 25 ETE: 50
4 Credits: 0 3
5 Semester: *
Autum Spring Both
n
6 Pre-Requisite: Basics of Automata Theory
7 Subject Area: Computer Science
8 Objective: To teach the students various concepts of NLP.
9 Course Outcome: After completion of the course students will be able to
CO 1 Classify the elements of Natural Language Processing (NLP)
CO 2 Describe and compare various parsing approaches used in NLP
CO 3 Analyze and Design the grammars to check the syntax and semantics
CO 4 Apply the different machine learning approaches in NLP
CO 5 Apply and evaluate different NLP strategies in Bigdata
CO 6 Compare and apply the tools for NLP
10 Details of the Course:
Unit CONTENT CONTACT
No. HOURS
1 Introduction to Natural Language Understanding: Overview, Applications 9
of NLP, Evaluating Language Understanding Systems, Different levels of
Language Analysis, Representations and Understanding, Organization of
Natural language Understanding Systems, NLP and Big Data.
2 Introduction to semantics and knowledge representation, Some 9
applications like machine translation, database interface. Grammars and
Parsing: Grammars and sentence Structure, Top-Down and Bottom-Up
Parsers, Transition Network Grammars, Top-Down Chart Parsing.
Feature Systems and Augmented Grammars: Basic Feature system for
English, Morphological Analysis and the Lexicon, Parsing with Features,
Augmented Transition Networks
3 Grammars for Natural Language: Auxiliary Verbs and Verb Phrases, 9
Movement Phenomenon in Language, Handling questions in Context-
Free Grammars. Human preferences in parsing, encoding uncertainty,
Deterministic Parser.
4 Ambiguity Resolution: Statistical Methods, Probabilistic Language 9
Graphic Era (Deemed to be University), 2021 / Review-02 Effective from Academic Year 2021-22
Processing, Estimating Probabilities, Part-of-Speech tagging, Obtaining
Lexical Probabilities, Probabilistic Context Free Grammars, Best First
Parsing. Semantics and Logical Form, Word senses and Ambiguity,
Encoding Ambiguity in Logical Form
5 Methods and tools of NLP analysis: Extracting and collecting information 9
from Twitter, Facebook and Internet pages; Sentiment analysis using big
data; Developing a recommender systems.
TOTAL 45
11 Suggested Books:
Sl. NO. NAME OF AUTHORS/BOOKS/PUBLISHERS YEAR OF
PUBLICATION
1 James Allen,” Natural Language Understanding”, 2/e, Pearson Education 2003
2 D. Jurafsky, J. H. Martin, “Speech and Language Processing”, Pearson 2002
Education
3 Charu C. Agarwal, “Recommender system: The Textbook”, 1/e, Springer 2016
Graphic Era (Deemed to be University), 2021 / Review-02 Effective from Academic Year 2021-22
