Speech and Natural Language Processing QUESTION PAPER
Speech and Natural Language Processing UTU QUESTION PAPER
BCST-803A/BITT-803A
Roll No.
Even Semester Examination, 2021-22
Course Name : B.TECH
Branch: Computer Science
Semester: VIII
Subject: Speech and Natural Language Processing
Time: 3 Hours
Note: Attempt all questions: All Questions carry equal marks
Max Marks: 100
Number of Printed pages: 2
Q1. Attempt any four parts of the following (5 x 4 = 20)
(a) List and explain the challenges of Natural Language Processing.
(b) What is meant by Lexicon? How is it useful in NLP?
(c) Distinguish between semantics, pragmatics and discourse.
(d) Identify the morphological type (Noun phrase, Verb Phrase, Adjective Phrase) of following sentence segments
1. important to Bill
2. Looked up the tree
(e) Explain the role of transformational rules in transformational grammar with the help of an example.
Q2. Attempt any four parts of the following (5 x 4 = 20)
(a) With a neat diagram describe how a typical NLP system is organized?
(b) What are the 2 main classes of tagging algorithms in which they can be grouped into? Explain each one in detail.
(c) How the natural language processing systems are evaluated? Explain.
(d) List the problems associated with N-gram model. Explain how these problems are handled. (e) Illustrate parts of Speech Tagging and explain different categories of POS tagging.
Q3. Attempt any two parts of the following (10 x 2 = 20)
(a) Write an algorithm for parsing a finite-state transducer using the pseudo code. Explain the algorithm with an example. Also give the merits and demerits of this algorithm..
(b) Analyze the naive Bayes classifier approach to Word Sense Disambiguation in NLP.
(c) Discuss the following:
(i) Language as a rule-based system. (ii) Stochastic Part-of-Speech tagging.
0 Comments