Natural Language Processing (AL-504 (B)) - Important Questions

Explain tokenization, stemming and lemmatization, compare stemming vs lemmatization, and their importance in morphological analysis for NLP.

Define formal grammar, explain its key components, and discuss its role/function in language modeling for NLP.

Define Natural Language Processing and explain its key components and challenges.

Define Natural Language Processing and explain its historical evolution from rule-based systems to deep learning models, including challenges in understanding, ambiguity, context and multilingual processing with examples.

Explain the need for Transducers in morphological parsing.

Write regular expression patterns for a given email address and spaced numeric string format

Describe stop word removal and normalization techniques and explain how text pre-processing improves NLP system performance.

Explain neural language models and compare traditional statistical language models with neural language models.

Explain the role and basic patterns of regular expressions in NLP with examples

Discuss finite-state automata and their relationship to regular expressions.

Explore the challenges associated with detecting and Correcting Spelling Errors in natural language text.

Write and explain the minimum edit distance algorithm.

Compare common types of smoothing techniques used in NLP and how they differ.

Compare Hidden Markov Models and Maximum Entropy models in terms of modeling approach, key components and probabilistic dependencies.

Explain Part-of-Speech tagging in detail and describe the different approaches such as rule-based, stochastic and neural approaches.

Write short notes on PoS tagging types and issues in word analysis.

Explain language models in NLP, describe N-gram language models and discuss their advantages and limitations.

Explain why n-gram models are limited in handling polysemy and ambiguity in language.

Explain the principles of rule-based including transformation-based POS tagging and how it improves tagging accuracy.

Explain what smoothing is in N-gram models, why it is necessary, with an example of how it works.

Explain with an example how bigram probability is calculated.

Explain how is perplexity calculated in evaluating N-grams.

Discuss the Hidden Markov Model in detail.

Explain how dependency grammar differs from phrase-structure grammar.

Describe disambiguation techniques and challenges in parsing

Check acceptance of a given string using the CYK algorithm for the grammar $S \rightarrow AB / BC, A \rightarrow BA / a, B \rightarrow CC / b, C \rightarrow AB / a$.

Explain syntax analysis / syntactic parsing in NLP, including top-down and bottom-up parsing techniques with suitable examples.

Explain context-free grammar, its key components and parse trees, and how they capture syntactic structure for syntactic analysis.

Explain ambiguity in NLP including lexical and syntactic / parse-tree ambiguity with examples

Explain any two of the following

What is the process involved in constructing treebanks, and how do they play a role in both the development and assessment of syntactic parsers?

Explain dependency grammar in detail.

Discuss in detail Probabilistic CYK.

Illustrate Word similarity using a thesaurus and distributional methods.

Briefly explain different bootstrapping methods in NLP.

Explain supervised Word Sense Disambiguation methods with suitable examples.

Explain semantic analysis in Natural Language Processing. Discuss meaning representation techniques, semantic roles, thematic relations and logical forms. Explain how semantic analysis helps in tasks such as question answering, information extraction and machine translation.

Discuss Word Sense Disambiguation (WSD) and explain different approaches used for WSD with examples.

Write short notes on Dictionary and Thesaurus, First order logic, and Tokenization.

Define what is Word Sense Disambiguation in NLP.

Explain the concept of compositional semantics and how it contributes to understanding the meaning of complex expressions?

Explain word sense disambiguation methods: supervised, dictionary-based, and thesaurus-based.

Explain quantifiers in detail with an example.

Explain major commercial and real-world applications of NLP and how they improve user experience and interaction

Explain speech recognition systems, their working principles, and how NLP enhances this technology

Explain machine translation including rule-based, statistical and neural approaches and compare them on accuracy, scalability and applications.

How can natural language processing create intelligent tutoring systems? Discuss with applications.

Describe the functioning of machine translation with real-world application examples.

Explain Text Summarization techniques and their applications.

How can natural language processing automate the authoring process? Discuss with applications.

What makes natural language querying possible through natural language processing?

Explain how NLP makes word processors smarter and more user-friendly.

Describe the transfer model of machine translation and its three phases.

Explain any two of the following:

Explain the levels of language analysis in NLP. Describe lexical, syntactic, semantic, discourse and pragmatic analysis with examples.

Write short notes on any two of the following: