University of Mumbai

M. Sc. Computer Science Semester II

Subject: NLP
Unit I 1. List and describe phases of NLP.
2. What are the challenges in NLP? How to overcome Ambiguity
faced while processing data?
3. Discuss N- gram model. Elaborate digram and trigam model with
example.
4. Define smoothing. Give the different types of smoothing
technique. Discuss any one of the techniques in detail.
5. How does NLP advantageous in day-to-day life?
6. What are the steps to build an NLP application?
7. State different types of ambiguities with example.
8. How does the noisy channel used for spelling correction?
9. What is n-gram model? Explain with chain rule of probability.
10. How does neural network model benefit in the development of
NLP application?
11. What is NLP? State and write one line on the different phases of
NLP.
12. Explain with example Named Entity Recognition?
13. Describe the various challenges and ambiguities faced by NLP.
14. State the characteristics of spaCy Library.
15. Explain in detail application of neural language model in NLP
system development.
16. Describe bi-gram and Tri-gram model with example.
17. Write a short note on NLTK.
Unit II 18. What is POS tagging? Explain in detail Rule- based POS tagging.
19. Define tagset. Explain the concept of tagset with the help of the
code snippet.
20. Discuss the concept of Treebank with the help of definition,
format, types and example.
21. Elaborate CKY parsing with example.
22. Explain Hidden Markov Model to embed POS tags in inputted
text.
23. Explain Lemmatization process with the help of python code.
24. How does POS tagging do with the help of TBL?
25. Compare Top-down parsing and Bottom-up parsing.
26. Write a short note on Probabilistic CKY.
27. State the working of neural network model in POS tagging.
28. What is Lemmatization? Explain with appropriate example.
 29. Define Corpus. Explain the role of Corpus in NLP.
30. What is Lemmatization? Explain with appropriate example.
31. Describe in brief Penn Treebank.
32. State the applications of Treebank.
33. Differentiate between the Top-down and Bottom Up Parsing.
Unit 34. Explain the concept of Vector Semantics with the help of Term
III Document Frequency model and Term Context model.
35. Write a short note on Word2vec.
36. Comment: Two words are similar in meaning if their context
vectors are similar.
37. Explain why there is a need of converting words to vector.
38. With the diagram discuss the working of Skip- Gram model.
39. How is CBOW model worked to find similarity?
40. What is WordNet? Explain the concept of WordNet with the help
of code snippet.
41. Write a note on vector semantics.
42. State the working of Tf-Idf.
43. How to measure semantics using dense vector?
44. Which are the techniques used in embedding with prediction?
Explain any one of the techniques.
45. Discuss the architecture of Skip-gram.
46. Illustrate the concept of word sense.
47. Briefly explain characteristics of LSA model.
48. What is WordNet? Describe the basic structure of the WordNet.
49. Explain how SVD is used in NLP. State the cons of SVD.
50. Describe how Continuous Bag of words used in embedding.
51. Explain in brief steps of LSA Implementation.
52. Comment on: “In Computational models of word meaning- If A
and B have almost identical environments, we say that they are
synonyms.
53. Write a short note on the tf-idf algorithm.
54. Write a short note on Pointwise Mutual Information Model.
Unit 55. Explain different types of machine translation.
IV
56. Discuss the Tutorial and Authoring system with the help of
example.
57. How is the speech recognition system used in NLP?
58. What are the commercial uses of NLP? Discuss any four in detail.
59. What is Pseudo translation? Explain the benefit of using Pseudo
translation.
60. Explain FFD filter used for translating file.
61. Explain the model for speech recognition.
62. In short explain the working of chat bot application.
63. How does NLP use in sentiment analysis?
64. How does customer feedback analyse with NLP techniques?
65. Explain the roll of NLP in semantic analysis.
66. Explain in brief applications of NLP in customer Service.
67. Describe the working of BERT model in detail.
68. Write a short note on: LSTM model?
69. Explain how NLP made man-machine interface easy.
70. What is the role of NLP in User Interface? Explain.