Scribd
Upload
132 views1 page

NLP Pyq

The document outlines a curriculum for Natural Language Processing (NLP) divided into six modules covering topics such as introduction to NLP, word level analysis, syntax analysis, semantic analysis, pragmatic and discourse processing, and applications. Each module contains specific questions and concepts to be discussed, including algorithms, models, and various linguistic phenomena. The document serves as a guide for understanding and exploring the complexities of NLP.

Uploaded by

Shubhankar Majgaonkar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
132 views1 page

NLP Pyq

The document outlines a curriculum for Natural Language Processing (NLP) divided into six modules covering topics such as introduction to NLP, word level analysis, syntax analysis, semantic analysis, pragmatic and discourse processing, and applications. Each module contains specific questions and concepts to be discussed, including algorithms, models, and various linguistic phenomena. The document serves as a guide for understanding and exploring the complexities of NLP.

Uploaded by

Shubhankar Majgaonkar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd

NLP PYQ

Module 1:Introduction
1. What is NLP? Explain ambiguity in NLP with example.
2. Discuss various challenges in processing natural language
3. What is NLP? Discuss various stages involved in NLP with example(+1)

Module 2: Word Level Analysis


1. Explain edit distance algorithm with an example. Show working min no of
operations requ. to transform 'kitten' into 'sitting'
2. Explain Porter's stemming algorithm with example
3. Explain N-gram model with example
4. FSA, FST
5. Predict next word in coupus numerical (MUST)
6. Explain in brief inflectional and derivational morphology with examples
7. Compare derivational and inflectional morphology with example

Module 3:Syntax analysis


1. What is POS tagging? List different approaches to POS tagging. Explain any one
approach in brief.
3. Explain the hidden Markov Model (HMM).
4. Explain in detail stochastic HMM tagging
5. top up and bottom up approach of parsing with example
6. Numerical compute conditional probability

Module 4:Semantic analysis


1. What is semantic analysis? Discuss different semantic relationship between the
words
2. Explain with suitable examples the following relationship between word meanings:
Homonymy, Plysemy, Synonymy, Hyponymy, Antonymy, Hypernomy, Meronomy (+1)
3. What is Word sense disambiguation? Explain dictionay based apporach to WSD
4. Short note - wordnet
5. What do you mean by WSD? Explain machine learning based (Naive based) approach
for WSD
6. Short note - wordnet

Module 5:Pragmatic and Discourse Processing


1. Explain Hobbs algorithm for pronoun resolution
2. Short note - Syntactic and semantic constraint on coreference (+1)
3. Short note - Reference Resolution problem

Module 6: Applications
1. What is Named-Entity recognition? Define its types (+1)
2. What is rule bas machine translation?
3. Short note - Information Retrieval, sentiment analysis
4. Discuss information retrieval vs information extraction
5. Short note - Machine translation

You might also like