B.Sc. (Computer Science) Sem 6 Information Retrieval Oct 2025 Question Paper - Mumbai University | munotes

Questions asked in this paper

• 2) Figures to the right indicate marks

1. Q3 Illustrations, in-depth answers and diagrams will be appreciated
2. Q4 Mixing of sub-questions is not allowed
3. Q1 Attempt ANY FOUR from the following: (20M)
   • (a) Explain the components of IR System
   • (b) by step explain the inverted index construction for the below given Document 1: The IR practical was conducted in CS lab Document 2: The CS lab was occupied whole day for a practical
   • (c) Write an algorithm to find Edit Distance. Use Edit Distance algorithm to find the edit distance between “sunday” and
   • (d) a short note on Vector Space Model
   • (e) various evaluation metrics used in information retrieval
   • (f) the different spelling correction techniques. Explain any one in detail
4. Q2 Attempt ANY FOUR from the following: (20M)
   • (a) Write a short note on Naive Bayes classification algorithm
   • (b) Diagrammatically explain web search architecture
   • (c) Briefly explain page rank algorithm. Give suitable example to explain the
   • (d) Discuss RankBoost
   • (e) the use of crawler. Explain in brief the working of crawler/ crawler
   • (f) Explain hierarchical clustering
5. Q3 Attempt ANY FOUR from the following: (20M)
   • (a) various dynamic web contents need to be taken care of during a (b) explain summarization. List the types of summarization and explain any one in detail
   • (c) the different approaches to find precise answers in Question Answering Write the challenges and techniques of multilingual retrieval
   • (f) the concept of A/B testing
6. Q4 Attempt ANY FIVE from the following: (15M)
   • (a) What are the challenges of IR? With the help example, elaborate the concept of HITS algorithm
   • (c) explain Surveys in information retrieval
   • (d) Define Boolean model along with a suitable example
   • (e) Write the applications of text categorization
   • (f) State the different web crawling techniques and explain any one in brief

Read from the scan above, so a character or two may differ. The scan is the original.