GUJARAT TECHNOLOGICAL UNIVERSITY

Program Name: Master of Engineering

Level: PG
Branch: Information Technology
Subject Code : ME02023011
Course / Subject Name : Natural Language Processing

w. e. f. Academic Year: A.Y. 2024-25

Semester: 2
Category of the Course: PCC

Prerequisite: Data structures& algorithms, finite automata, probability theory and basic
programming.
Rationale: This course aims to provide students with fundamentals and working of
NLP and enable student to apply it.
Course Outcome:
After Completion of the Course, Student will able to:
N RBT
Course Outcomes
o Level
1 Understand various levels of analysis involved in NLP. U
2 Understand language generation and discourse analysis U
3 Able to design, implement, and analyze NLP algorithms A
Explore various application of NLP like Machine Translation, Text Summari N
4
zation
*Revised Bloom’s Taxonomy (RBT)

Teaching and Examination Scheme:

Total
Teaching Scheme Credits
Assessment Pattern and Marks
(in Hours) L+T+
(PR/2) Total
Marks
Theory Tutorial / Practical
L T PR C ESE PA / CA PA/CA ESE
(E) (M) (I) (V)
3 0 2 4 70 30 20 30 150

Course Content:
Unit No. of % of
Content
No. Hours Weightage
Introduction
Introduction to NLP. NLP tasks in syntax, semantics, and pragmatics.
1. Applications such as information extraction, question answering, and 3 10
machine translation. The problem of ambiguity. The role of machine
learning. Brief history of the field.

w.e.f. 2024-25 https://syllabus.gtu.ac.in/ Page 1 of 3

 GUJARAT TECHNOLOGICAL UNIVERSITY
Program Name: Master of Engineering
Level: PG
Branch: Information Technology
Subject Code : ME02023011
Course / Subject Name : Natural Language Processing

N-gram Language Models

N-grams Models of Syntax - Counting Words - Unsmoothed N-grams.
Smoothing- Back-off Deleted Interpolation – Entropy - English Word
2. 10 20
Classes - Tag sets for English Part of Speech Tagging-Rule Based Part
of Speech Tagging - Stochastic Part of Speech Tagging -
Transformation-Based Tagging
Context Free Grammars
Context Free Grammars for English Syntax- Context-Free Rules and
Trees -Understand the network simulation tools. Sentence- Level
3 7 15
Constructions–Agreement – Sub Categorization .Parsing – Top-down
– Early Parsing -feature Structures – Probabilistic Context-Free
Grammars
Semantic Analysis: Representing Meaning-Meaning Structure of
Language-First Order Predicate Calculus Representing Linguistically
Relevant Concepts -Syntax-Driven Semantic Analysis - Semantic
4 7 15
Attachments -Syntax-Driven Analyzer. Robust Analysis - Lexemes
and Their Senses - Internal Structure - Word Sense Disambiguation -
Information Retrieval
Language Generation And Discourse Analysis: Discourse -
Reference Resolution - Text Coherence -Discourse Structure –
Coherence. Dialog and Conversational Agents - Dialog Acts –
5. 7 15
Interpretation -Conversational Agents. Language Generation–
Architecture-Surface Realizations - Discourse Planning .Machine
Translation -Transfer Metaphor– Interlingua – Statistical Approaches
Information Extraction (IE): Named entity recognition and relation
6. 3 10
extraction. IE using sequence labeling.
Machine Translation (MT):
7. Basic issues in MT. Statistical translation, word alignment, phrase- 4 10
based translation, and synchronous grammars.
Applications of NLP : Sentiment Analysis, Chatbot, Text
8. 4 5
Summarization, Question/Answering
TOTAL 45 100

Suggested Specification Table with Marks (Theory):

Distribution of Theory Marks (in %)
R Level U Level A Level N Level E Level C Level
- 40 30 30 -- ---
Where R: Remember; U: Understanding; A: Application, N: Analyze and E: Evaluate C:
Create (as per Revised Bloom’s Taxonomy)

w.e.f. 2024-25 https://syllabus.gtu.ac.in/ Page 2 of 3

 GUJARAT TECHNOLOGICAL UNIVERSITY
Program Name: Master of Engineering
Level: PG
Branch: Information Technology
Subject Code : ME02023011
Course / Subject Name : Natural Language Processing

References/Suggested Learning Resources:

(a) Books:

1. D. Jurafsky and J. Martin “Speech and Language Processing: An Introduction to Natu

ral Language Processing, Computational Linguistics, and Speech Recognition”, Third
Edition draft
2. C. Manning and H. Schutze, “Foundations of Statistical Natural Language
Processing”,MIT Press, 1999
3. Bharati A., Sangal R., ChaitanyaV.. Natural language processing: a Paninian
perspective, PHI, 2000
4. Siddiqui T., Tiwary U. S. Natural language processing and Information retrieval, OUP
2008

(b) Open source software and website:

1. NPTEL Course: Natural Language Processing, IIT Kharagpur by Prof. Pawan

Goyal

Suggested Course Practical List: (List can be change according to Latest Development)

Sr Aim
1 Basic Text Processing operation on text document
2 Implement N‐gram Language model
3 Write a program to extract features from text
4 Implement word embedding using Word2Vec/Glove/fastText
5 Implement LSA and Topic model
6 Implementation text classification using Naïve Bayes, SVM
7 Implementation of K‐means Clustering algorithm on text
8 Implement PoS Tagging on text
9 Implement text processing with neural network
10 Implement text processing with LSTM
11 Implement HMM/CRF on sequence tagging task
12 Develop any one NLP application
 Sentiment Analysis
 Chatbot
 Text Summarization
 Question/Answering

*******

w.e.f. 2024-25 https://syllabus.gtu.ac.in/ Page 3 of 3