CS6007 INFORMATION RETRIEVAL Nov Dec 2017 Question Paper

Anna University B.E / B.Tech CS6007 INFORMATION RETRIEVAL Nov Dec 2017 Question Paper

Anna University Chennai

Question Paper Code : 50369

B.E/B.Tech. DEGREE DGMINATION NOVEMBER/DECEMBER 2017

Seventh Semester

Computer Science and Engineering

CS 6007 - INFORMATION RETRIEVAL

(Regulations 2013)

Time : Three Hours

Maximum: 100 Marks

Answer ALL questions

Part A - (10x2=20 Marks)

1. What is peer-to-peer search ?

2. What are the performance measures for search engine ?

3. What is Zone index ?

4. State Bayes rule.

5. What are politeness policies used in web crawling ?

6. What is inversion in indexing process ?

7. What is snippet generation ?

8. List the characteristics of Map Reduce Strategy.

9. Differentiate supervised and unsupervised learning.

10. What is Dendrogram ? 

PART - B (5x16=80 Marks)

11. a) i) Differentiate between Information Retrieval and Web Search. (8)

ii) Explain the issues in the process of Information Retrieval. (8)

(Or)

b) Explain in detail, the components of Information Retrieval and Search engine. (16)

12. a) Write short notes on the following :

i) Probabilistic relevance feedback.

ii) Pseudo relevance feedback.

iii) Indirect relevance feedback.

(OR)

b) i) Explain in detail about binary independence model for Probability Ranking Principle (PRP). (10)

ii) Describe how the query generation probability for query likelihood model can be estimated.

13. a) Write short notes on the following :

i) Focused crawling

ii) Deep web

iii) Distributed crawling

iv) Site map.

(OR)

b) Explain in detail about finger print algorithm for near-duplicate detection. (8)

ii) Brief about search engine optimization. (8)

14. a) i) Explain in detail about Community-based Question Answering system. (10)

ii) Brief on Personalized search. (6)

(OR)

b. i) Explain in detail, the Collaborative Filtering using clustering technique. (10)

ii) Brief about HITS algorithm. (6)

15. a) Explain in detail the Multiple-Bernoulli and the multinominal models. (16)

(OR)

i) Explain the process of choosing K in K-nearest neighbor clustering. 

ii) Brief about Expectation Maximization algorithm.

Share This