Natural Language Processing (NLP) SPPU Endsem Question Paper Nov 2023
All 8 questions from this SPPU endsem paper, as printed. Read them here or open the PDF.
- Subject code
- 410252A
- Pattern
- 2019 pattern
- Exam
- Endsem
- Session
- Nov 2023
- Max. marks
- 70
- Time
- 2½ Hours
- Semester
- VIII
- Paper code
- [6181]-116
Printed for: B.E. (Computer Engineering)
Instructions to the candidates
- All questions are compulsory.
- Figures to the right indicate full marks.
Questions
Q1
- a)[4]
What are generative models of language? Explain any one model in detail.
Also asked:Nov 2024
- b)[8]
Consider the following small corpus: Training corpus: <s> I am from Pune </s> <s> I am a teacher </s> <s> students are good and are from various cities </s> <s> students from Pune do engineering </s> Test data: <s> students are from Pune </s> Find the Bigram probability of the given test sentence.
- c)[6]
OR- a)
Q2
- a)[4]
Write short note on BERT.
- b)[6]
This part has equations that don’t show as text. Open the PDF to read it.
- c)[8]
Describe the Latent Dirichlet Allocation (LDA) algorithm and how it is used for topic modeling?
Also asked:May 2023
- a)
Q3
- a)[4]
Describe the concept of Information Retrieval. Explain the significance of Natural Language Processing in Information Retrieval.
Also asked:May 2023
- b)[8]
Explain reference resolution and conference resolution with example.
- c)[6]
What is Cross-Lingual information Retrieval, and how is it used in Natural Language Processing? Provide an example.
Also asked:May 2023
OR- a)
Q4
- a)[6]
Explain the concept of the Vector Space Model, and describe how it is used in Information Retrieval.
- b)[8]
Describe entity extraction and relation extraction with the help of examples.
- c)[4]
What is Named Entity Recognition (NER)? Describe the various metrics used for evaluation.
Also asked:May 2023
- a)
Q5
ORQ6
- a)[10]
Explain the following lexical knowledge networks? i) WordNet ii) Indo WordNet iii) VerbNets iv) PropBank v) Treebanks
Also asked:Nov 2024
- b)[7]
Write Python code using NLTK library to split the text into tokens using whitespace, punctuation-based and default tokenization methods.
- a)
Q7
ORQ8