Scribd
Upload
59 views3 pages

NLP Imp Question

Uploaded by

mohdsahilk841
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
59 views3 pages

NLP Imp Question

Uploaded by

mohdsahilk841
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

NATURAL LANGUAGE PROCESSING

Module 1: Introduction to NLP


1. Define Natural Language Processing (NLP) and discuss its applications with
examples.
2. Explain the concept of ambiguity in natural languages, providing examples.
3. What are the challenges in NLP? Discuss how they affect language processing tasks.
4. Describe the levels of NLP (phonology, morphology, syntax, semantics, pragmatics).

Module 2: Word Level Analysis


1. Explain Tokenization, Stemming, and Lemmatization with examples. How are they
different?
2. Define morphological analysis and explain the difference between inflectional and
derivational morphology with examples.
3. What is edit distance? Explain the edit distance algorithm with a step-by-step
example.
4. What is a finite state transducer (FST)? Explain its role in word analysis.
5. Discuss collocations and their importance in language processing.

Module 3: Syntax Analysis


1. What is POS tagging? Describe the different approaches to POS tagging (rule-based,
stochastic, transformation-based).
2. Explain the Hidden Markov Model (HMM) and its application in POS tagging.
3. List and explain various POS tagging methods with examples.
4. What is a context-free grammar (CFG)? Explain its use in syntax analysis.
5. Describe Conditional Random Fields (CRF) and their use in NLP.

Module 4: Semantic Analysis


1. Define semantic analysis and discuss different types of semantic relationships like
homonymy, polysemy, synonymy, and hyponymy.
2. What is Word Sense Disambiguation (WSD)? Describe dictionary-based approaches,
such as Lesk's Algorithm.
3. Explain knowledge-based, supervised, semi-supervised, and unsupervised
approaches to WSD.
4. Discuss WordNet and its role in NLP. How is it used for semantic analysis?
5. Explain semantic ambiguity and how it is handled in NLP.

Module 5: Pragmatics and Discourse Processing


1. What is reference resolution? Discuss the importance of anaphora resolution in
NLP.
2. Explain Hobbs Algorithm for pronoun resolution with an example.
3. Discuss coreference in discourse processing. Why is it significant for NLP
applications?
4. What are syntactic and semantic constraints in discourse analysis?
5. Describe discourse reference resolution and its challenges in natural language.

Module 6: Applications of NLP


1. Explain the process of machine translation and its challenges, with a focus on rule-
based approaches.
2. What is information retrieval? Explain how it is applied in NLP.
3. Describe sentiment analysis and its applications in NLP. How does it differ from other
types of text classification?
4. What is Named-Entity Recognition (NER)? Discuss its types with examples.
5. Explain the role of question-answering systems and summarization in NLP
applications.

Linguistic Modeling and Tools


1. Describe WordNet, BabelNet, or similar lexical databases and their application in
NLP.
2. Discuss Hidden Markov Models (HMMs) and their relevance in modeling sequential
data.
3. Explain maximum entropy models and how they are used in NLP for tasks like POS
tagging.
4. Describe Finite Automata and their application in NLP.
5. What are neural language models? Explain how they differ from traditional n-gram
models.
Observed Trends for Each Module
 Algorithms and Step-by-Step Explanations: Frequently asked for edit distance,
Lesk’s algorithm, Hidden Markov Model, and Hobbs Algorithm.
 Concept Definitions and Comparisons: Expect questions on the differences between
morphological types, ambiguity types, and tagging approaches.
 Practical Applications: Modules 6 and 7 often focus on real-world applications like
machine translation, sentiment analysis, NER, and language models.
 Core NLP Tasks: POS tagging, syntax analysis, semantic relationships, and reference
resolution questions are frequently asked across Modules 3-5.

You might also like