MCSCS106-3 Natural Language Processing M.Tech Model Question Paper : mgu.ac.in

Name of the College : Mahatma Gandhi University
Department : Computer Science and Engineering
Subject Code/Name : MCSCS 106-3/NATURAL LANGUAGE PROCESSING
Sem : I
Website : mgu.ac.in
Document Type : Model Question Paper

Download Model/Sample Question Paper :
I : https://www.pdfquestion.in/uploads/mgu.ac.in/5017-1-MCSCS%20106-3%20Natural%20Language%20Processing%20set1(1).doc
II : https://www.pdfquestion.in/uploads/mgu.ac.in/5017-2-MCSCS%20106-3%20Natural%20Language%20Processing%20set2(1).doc

MGU Natural Language Processing Question Paper

M.TECH. DEGREE EXAMINATION :
Branch: Computer Science and Engineering
Specialization : Computer Science and Engineering

Related : MGU MCSCS106-1 Data Mining Concepts M.Tech Model Question Paper : www.pdfquestion.in/5016.html

Model Question Paper – II :
First Semester

MCSCS 106-3

NATURAL LANGUAGE PROCESSING (Elective ?I)
(Regular – 2013 Admission onwards)
Time: 3hrs
Maximum:100 marks
Answer the following Questions :
1. a) Explain the porter stammer .(15)
b) Discuss the different models and algorithms.(10)
or
2. a) Explain Finite-State Morphological parsing.(13)
b) Explain Regular Expressions and Finite-State automata .(12)

3. a) Explain the different word classes and part-of-speech tagging (25)
or
4. a) Write an algorithm for simple top-down parser with an example.(13)
b) Explain the terms verb phrases and simple sentences,five verb forms and some common
verb compliment structure in English. (12)

5. a) How Parsing is done with unification constraints? (13)
b) Explain how unification is implemented .(12)
or
6. a) Discuss dependency grammar and probabilistic lexicalized CFGs.Also explain the feature structures and how unification is done in it. (25)

7. a) Between the words eat and find which would you expect to be more effective in selecting
restriction-based sense disambiguation .(20)
b) Explain the application of semantics.(5)
or
8. a) Describe Syntax-Driven semantic analysis and Robust semantic analysis with examples.(25)

MCSCS 106-3

NATURAL LANGUAGE PROCESSING : (Elective ?I)
(Regular – 2013 Admission onwards)
Time: 3hrs
Maximum:100 marks
Answer the following Questions :
1. a) Write an algorithm for parsing a finite-state transducer using the pseudocode with an example.Also specify the merits and demerits of this algorithm.(25)
or
2. a) Explain the issues in computational morphology with suitable example.(20)
b) Discuss the applications of natural language processing (5)

3. a)Discuss language as a rule-based system. (13)
b)Discuss stochastic part-of-speech tagging.(12)
or
4. a) Write an algorithm for simple top-down parser with an example.(20)
b)Explain the five verb forms. (5)

5. a)Describe unification method with suitable examples. (13)
b)Explain how unification is implemented .(12)
or
6. a) Discuss Lexicalized parsing ,probabilistic parsing and human parsing(25)

7. a) Between the words eat and find which would you expect to be more effective in selecting
restriction-based sense disambiguation .(20)
b) Explain the application of semantics.(5)
or
8. a) Describe the different types of semantic analysis with example.(25)

Syllabus

Module 1 :
Introduction – Knowledge in speech and language processing – Ambiguity – Models and Algorithms – Language, Thought and Understanding.

Regular Expressions and automata : Regular expressions – Finite-State automata. Morphology and Finite-State Transducers: Survey of English morphology – Finite-State Morphological parsing – Combining FST lexicon and rules – Lexicon-Free FSTs: The porter stammer – Human morphological processing

Module 2 :
Syntax – Word classes and part-of-speech tagging : English word classes – Tagsets for English – Part-of-speech tagging – Rule-based part-of-speech tagging – Stochastic part-of-speech tagging – Transformation-based tagging – Other issues.

Context-Free Grammars for English: Constituency – Context-Free rules and trees – Sentence-level constructions – The noun phrase – Coordination – Agreement – The verb phase and sub categorization – Auxiliaries – Spoken language syntax – Grammars equivalence and normal form – Finite-State and Context-Free grammars – Grammars and human processing.

Parsing with Context-Free Grammars : Parsing as search – A Basic Top-Down parser – Problems with the basic Top-Down parser – The early algorithm – Finite-State parsing methods.

Module 3 :
Advanced Features and Syntax – Features and Unification : Feature structures – Unification of feature structures – Features structures in the grammar – Implementing unification – Parsing with unification constraints – Types and Inheritance.

Lexicalized and Probabilistic Parsing Probabilistic context-free grammar – problems with PCFGs – Probabilistic lexicalized CFGs – Dependency Grammars – Human parsing.

Module 4 :
Semantic Representing Meaning – Computational desiderata for representations – Meaning structure of language – First order predicate calculus – Some linguistically relevant concepts – Related representational approaches – Alternative approaches to meaning.

Semantic Analysis : Syntax-Driven semantic analysis -Attachments for a fragment of English – Integrating semantic analysis into the early parser – Idioms and compositionality – Robust semantic analysis.

Lexical semantics : relational among lexemes and their senses – WordNet: A database of lexical relations – The Internal structure of words – Creativity and the lexicon. Application: Word sense Disambiguation.

References :
1. Daniel Jurafsky & James H.Martin, “Speech and Language Processing”, Pearson Education (Singapore) Pte. Ltd., 2002.
2. James Allen, “Natural Language Understanding”, Pearson Education, 2003.