Scribd
Upload
47 views3 pages

CS 6030 Natural Language Processing

This document outlines the syllabus and examination structure for the CS6030-Natural Language Processing course at Anna University for the seventh semester. It details the course objectives, assessment format, and specific topics covered in the exam, including linguistics, machine learning techniques, and statistical approaches to machine translation. The exam consists of three parts: Part-A with short answer questions, Part-B with detailed questions, and Part-C with comparative analysis.

Uploaded by

SRIVARSHIKA Sudhakar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
47 views3 pages

CS 6030 Natural Language Processing

This document outlines the syllabus and examination structure for the CS6030-Natural Language Processing course at Anna University for the seventh semester. It details the course objectives, assessment format, and specific topics covered in the exam, including linguistics, machine learning techniques, and statistical approaches to machine translation. The exam consists of three parts: Part-A with short answer questions, Part-B with detailed questions, and Part-C with comparative analysis.

Uploaded by

SRIVARSHIKA Sudhakar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

ROLL NO:

ANNA UNIVERSITY
B.E./B.TECH/B.ARCH/ (FULL TIME) - END SEMESTER EXAMINATIONS,
NOV/DEC-2023
COMPUTER SCIENCE AND ENGINEERING
SEVENTH SEMESTER
CS6030-NATURAL LANGUAGE PROCESSING (RUSA ZOlfl)

Time: 3 hrs Max. Marks 100

COl To Understand basics of Linguistics, Probability & Statistics


C02 To Study Concepts of Morphology, Syntax, Semantics & Pragmatics
C03 To Learn various Machine Learning Techniques used in NLP
C04 To Understand Statistical Approaches to Machine Translation
COS To Understand Deep Learning for NLP
BL- Bloom's Taxonomy Levels
(Ll-Remembering, L2- Understanding, L3-App!ying, L4-Analysing, L5-Evaluating, L6-Creating)

Part-A (10*2=20)

Answer all Questions

SI.No Answer the following Marks CO Bloom

1 Give example statements for Pragmatic Ambiguity. 2 2 3


2 What are the applications of Earley Algorithm? 2 2 2

3 Define: Term Frequency, Inverse Document Frequency 2 3 1


4 Identify the Morphological Type: 2 2 2
1. Important to Bill 2. Looked Up the Tree
5 Distinguish: Anaphora & Cataphora 2 2 2
6 Draw the block diagram for N-gram Topic Modelling. 2 5 6
7 What are the challenges in handling Word Sense 2 4 2
Disambiguation during Machine Translation?
8 What is LSI? 2 1 1
9 Why is Independence assumption followed in Naive Bayes? 2 1 4
10 How is Bag-of-words model useful in Machine Translation? 2 4 5
Part-B (8*8=64)

(Answer any 8 Questions)

SI.No Answer the following Marks CO Bloom

11 Explain Dependency Parsing with 2 examples of your choice. 8 2 3


12 Discuss various POS tags in English. Provide an example text 8 2
and tag the POS within the text using POS markers.

13 Explain Lexicon, Lexeme and the different types of relations 8 2 2


that hold between lexemes.

14 Is ABSTRACT a summary of research paper? Explain with 8 4 3


block diagram on arriving at a better summarisation system,
if any.

15 Discuss ways of using word embedding using pre-trained 8 5 3


Language Model? Justify.

16 Discuss the processes involved in creating a Recommender 8 5 4


System for Re-targeted Ads Generation in Social Media.
Please depict using a block diagram and support with an
explanation.

17 Draw ambiguous parse trees for "1 saw a man with a 8 2 2


telescope" and "1 saw a man with a telescope on the boat".
Explain the ambiguity.

18 Discuss with block diagram how Language Models are used in 8 4 5


developing a Mobile App for Dyslexia Children.
19 Explain and Show examples for distinguishing Information 8 3 4
Extraction vs. Information Retrieval.
20 How do you apply Machine Translation techniques to 8 4 6
dynamically translate the Quora results? Explain with block
diagram.
21 State & Explain any 3 different evaluation metrics available 8 3 2
for Text Classification.
22 Explain Vector Space Model with neat illustrated example. 8 3 3

Part-C (8*2=16)

SI.No Answer the following Marks CO Bloom

23 Compare and Contrast word embedding models through 1 8 3 4


sample example paragraph.
24 Give a sample paragraph and explain the process for 8 2 5
obtaining N-grams from the text.

You might also like