GH Raisoni College of Engineering & Management, Pune

TY B. Tech.

Blooms Taxonomy level

1: Remember, 2: Understand,3: Apply, 4: Analyse, 5: Evaluate, 6: Create

Natural Language Processing (UAIL303/UCAIL303)

ESE

Q. No. Question Marks BL CO PO

UNIT I
1. Discuss lexical semantic analysis. [5] 2 1 1
2. Explain the concept of stemming lemmatization. [5] 2 1 1
3. Explain Basic text processing with examples. [5] 2 1 2
4. Explain the NLP pipeline process in detail. [5] 2 1 1
5. Illustrate different phases of NLP. [5] 3 1 1
6. Explain any two spelling correction methods. [5] 2 1 1
7. Discuss approximate string matching technique. [5] 2 1 1
8. Discuss coarse search technique and fine search technique in [5] 2 1 1
detail.
9. Explain any three spelling correction techniques in detail. [5] 2 1 1
10. Discuss statistical language modelling. [5] 2 1 1
11. Explain any four types of smoothing techniques in NLP [5] 2 1 1
12. Illustrate additive smoothing and backoff and interpolation [5] 3 1 1
smoothing technique in NLP.
UNIT II
13. Illustrate Max Entropy Model with assumptions. [5] 3 2 1
14. Discuss Parsing in detail. [5] 2 2 1
15. Explain Constituency Parsing [5] 2 2 1
16. Explain Dependency Parsing in Syntax. [5] 2 2 1
17. What is Parsing? Mention its types. [5] 2 2 1
18. Illustrate Conditional Random Field. [5] 3 2 1
19. Compare Constituency Parsing and Dependency Parsing. [5] 3 2 1
Unit III
20. Explain Lexical Semantics with relation between lexical [5] 2 3 1
items.
21. Discuss Topic Modeling with topic modeling techniques. [5] 2 3 1
22. Discuss Topic Analysis with its Scope. [5] 2 3 1
23. Explain Topic Analysis with its Importance. [5] 2 3 2
24. Discuss Entity linking with Name Entity Linking. [5] 2 3 1
25. Discuss Semantic Analysis with its applications. [5] 2 3 1
26. Illustrate Topic Modeling with applications. [5] 3 3 1
27. Define Lexical semantics, word senses and homonyms. [5] 1 3 1
28. Illustrate synonymy, antonymy and hypernymy. [5] 3 3 1
29. Describe Latent semantic analysis(LSA) algorithm. [5] 2 3 1
Unit IV
30. Discuss Text Classification with three approaches. [4] 2 2 1
31. Describe Information Extraction with the Information [6] 2 2 1
Extraction NLP techniques any three..
32. Illustrate General Pipeline of Information Extraction [4] 3 2 1
Process.
33. Explain Text Summarization classification on a different [6] 2 2 1
basis.
34. Discuss Text Summarization with advantages and [4] 2 2 1
application of Text Summarization.
35. Illustrate Rule based matching technique [3] 3 2 1
36. Distinguish between Extraction based summarization and [3] 3 2 1
abstractive summarization.
37. Explain Text summarization on the basis of context of text. [3] 2 2 1
38. Explain the steps for creating a text classifier. [4] 2 2 1
39. Illustrate token based matching technique [4] 3 2 1
Unit V
40. Illustrate the basic working flow of sentimental analysis. [5] 3 4 1
41. Explain sentimental analysis with its benefits. [5] 2 4 1
42. Discuss the types of sentimental analysis. [5] 2 4 1
43. Differentiate between emotion base and aspect base [5] 3 4 1
sentimental analysis.
44. Explain fine grained sentiment analysis. [5] 2 4 1
45. Illustrate the use of sentimental analysis. [5] 3 4 1
46. Discuss the types of sentimental analysis with examples. [5] 2 4 1
47. Discuss opinion mining with its different techniques and [5] 2 4 1
types
48. Explain different data visualization types for results of [5] 2 4 1
sentiment analysis
49. Explain rule based, automatic and hybrid approaches of [5] 2 4 1
sentiment analysis.
50. Discuss challenges of machine based sentiment analysis. [5] 2 4 1