NLP – Question bank
Unit 1
1. What is NLP? Explain any five applications of NLP.
2. Explain the Challenges that can be faced while designing NLP software.
3. Describe NLP abstraction levels in short.
4. What are various Characteristics of Natural Language? Explain in detail.
5. Describe various NL computing techniques and steps in detail.
6. What are various ways to create segmentation of written text into meaningful units?
7. Write a short note on one of the natural language tasks – Tagging.
8. What is chunking in NLP? What are the Rules for Chunking?
9. Write a short note on Named Entity Recognition.
10. Describe text parsing in NLP.
11. What Types of ambiguity available in NLP? Describe various Approaches and
Methods to Word Sense Disambiguation.
12. How NL Generation works? Explain in detail.
13. Define Sentiment Analysis. Explain its classification levels.
14. Explain Text Entailment with examples.
15. Write a brief note on Cross Lingual Information Retrieval.
16. How Space-Delimited Languages tokenize a word? Describe in brief.
17. What are common approaches to tokenize a word in Unsegmented Languages?
How is word segmentation done in Chinese and Japanese languages
18. How Sentences can be delimited in most written languages? Write about
Sentence Boundary Punctuation.
19. How Sentences can be delimited in most written languages? Write about the
importance of Context.
20. How Sentences can be delimited in most written languages? Write about the
Traditional Rule-Based Approaches.
21. How Sentences can be delimited in most written languages? Write about the
Robustness and Trainability.
22. What is lexical analysis? Explain in brief. Also explain Finite state Automaton
NLP – Question Bank
Prepared by: Ms. Beena Kapadia
Vidyalankar School of Information Technology
with its network.
23. What is lexical analysis? Also explain how Finite State Automaton (FSA)
converts Noun from Singular to Plural.
24. Write a brief note on Lexicon in Finite State Automaton (FSA).
25. What is lexical analysis? how Finite State Transducers Converts plural to
singular (lemma).
26. Describe Two level morphology in detail.
27. Write a brief note on Finite State Morphology.
28. Explain “Difficult” Morphology and Lexical Analysis.
Unit 2
1. What is Syntactic parsing? What are the difficulties in creating Syntactic parsing?
2. How syntactic parsing can be done using Context Free Grammar? Explain with example.
3. Describe various syntactic parsing techniques.
4. What are the Basic Concepts in Parsing?
5. Build the syntactic parsing tree using the following sentence and the grammar given. Apply top
down and bottom up approaches.
I/P :- Book that flight
S -> VP
VP -> VP NP
NP -> Det NP
Det -> that
NP -> singular Noun
singular Noun -> flight
Verb -> book
6. How to Implement Deductive Parsing? Explain with respect to Agenda-Driven Chart Parsing.
7. How to Implement Deductive Parsing? Explain with respect to Storing and Retrieving Parse
Results.
8. Explain in detail about LR syntactic Parsing.
9. What are the Issues in Parsing? Explain in detail.
10. What are the Basic Concepts and Issues in Natural Language Semantics? Explain in detail.
11. Explain Logical Approaches to Semantic Representation in detail.
NLP – Question Bank
Prepared by: Ms. Beena Kapadia
Vidyalankar School of Information Technology
12. Explain Discourse Representation Theory approach to Semantic Representation in detail.
13. Explain Pustejovsky’s Generative Lexicon approach to Semantic Representation in detail.
14. Explain Natural Semantic Metalanguage approach to Semantic Representation in detail.
15. What are various Theories and Approaches to Semantic Representation? Explain Object-Oriented
Semantics approach to Semantic Representation in detail.
16. Write a short note on Relational Issues in Lexical Semantics.
17. Explain Functional Macro-Categories with respect to fine-grained lexical-semantic analysis.
18. What is Natural language generation? How generation can be compared with comprehension?
19. What is Natural language generation? What are the issues in it?
20. What are the components of a natural language generator? Explain each one in short.
21. Explain The Function of the Speaker approach to Text Planning in natural language generation.
22. Explain Desideratum for Text Planning and Pushing vs. Pulling approach in natural language
generation.
23. What are various approaches to Text Planning in natural language generation? Explain Planning
by Progressive Refinement of the Speaker’s Message in detail.
24. Explain Planning Using Rhetorical Operators approach to Text Planning in natural language
generation.
25. Explain Text Schemas approach to Text Planning in natural language generation.
26. What are the Linguistic Components in Natural Language generation? Explain each one in short.
Unit 3
1. What are the common problems with part of speech tagging systems? Describe In detail.
2. Describe the General Framework of part of speech tagging.
3. How rule-based approaches work in part of speech tagging? Also write about its two-stage
architecture and properties.
4. Which approaches are applied by the simplest stochastic tagger? Also, write about
Properties of Stochastic POS Tagging.
5. What is transformation-based learning? Also, explain the working of Transformation Based
Learning.
6. What is transformation-based learning? Write its advantages and disadvantages.
7. What is transformation-based learning? what are the Modifications to TBL and Other Rule-
Based Approaches?
8. What is Hidden Markov Model? Also, explain the use of HMM for Part of Speech Tagging.
9. What are the drawbacks of Hidden Markow Model? How Maximum Entropy Models
overcome the drawbacks of HMM?
10. What is confusion matrix? What are its four basic terminologies? Also write the definition
and formula of accuracy, precision and recall.
Unit 4
NLP – Question Bank
Prepared by: Ms. Beena Kapadia
Vidyalankar School of Information Technology
1. Explain constituent structure and dependency structure for an English sentence with a neat
diagram with respect to Syntactic Representations of Statistical Parsing.
2. Write in brief about Statistical Parsing Models. Also, explain Parser Evaluation in Statistical
Parsing.
3. How PCFGs work as Statistical Parsing Models? Explain with a neat diagram.
4. Describe Generative Models. Also compare it with PCFG model.
5. Describe History-Based Models in detail.
6. Write a brief note on PCFG Transformations.
7. Describe the standard version of Data-Oriented Parsing in detail.
8. Explain the working of Local Discriminative Models in detail.
9. Explain the working of Global Discriminative Models in detail.
10. Explain in brief about Beyond Supervised Parsing, Weakly Supervised Parsing and
unsupervised parsing.
11. What is Indian Language Parsing in Paninian Karaka Theory? Explain with respect to a default
karaka chart and transformation rules.
12. What is constraint-based parsing? Explain in detail with respect to Paninian Karaka Theory.
13. What is malt-parsing? Explain in brief with respect to Inductive Dependency Parsing.
14. Write a brief note on Parsing Algorithms of malt parsing.
15. Explain Feature Models in brief with respect to malt parsing.
16. What is Learning Algorithms in malt parsing? Also write about Learning and Parsing.
Unit 5
17. What is MWEs? Explain Linguistic Properties of MWEs Idiomaticity property of its in detail.
18. Describe Lexical Idiomaticity and statistic Idiomaticity of MWEs.
19. Describe Syntactic Idiomaticity and Semantic Idiomaticity of MWEs.
20. Describe Lexical Idiomaticity and Pragmatic Idiomaticity of MWEs.
21. How to Test an Expression for MWEhood? Explain in detail.
22. What are the Types of MWEs? Explain Verbal MWEs in detail.
23. What are the Types of MWEs? Explain Nominal MWEs and Prepositional MWEs in detail.
24. Why do we use normalized web distance? Explain any two methods of it.
25. Explain Association Measures and Attributes methods for Word Similarity.
26. Describe Relational Word Similarity and Latent Semantic Analysis methods for Word
Similarity.
27. What is Kolmogorov Complexity? Explain in brief.
28. Define Information Distance. Also explain Normalized Information Distance.
29. Define Information Distance. Also explain Normalized Compression Distance.
30. Write a brief note on Applications and Experiments of Normalized word
NLP – Question Bank
Prepared by: Ms. Beena Kapadia
Vidyalankar School of Information Technology
