• Attempt any five questions.
• All questions carry equal marks.
Define Natural Language Processing, what are the key components and challenges of it.
Discuss finite-state automata and their relationship to regular expressions.
Explain the morphological analysis using stemming and lemmatization processes.
How do the modeling approaches of Hidden Markov Models and Maximum Entropy differ in terms of probabilistic dependencies?
Compare common types of smoothing techniques used in natural language processing.
Why are n-gram models limited in their ability to handle polysemy and ambiguity in language?
Describe disambiguation techniques and challenges in parsing.
Check the acceptance of string s="baabs" using the CYK Algorithm for the given grammar S AB/BC A BA/a B CC/b C AB/a
Explain how dependency grammar differs from phrase-structure grammar.
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.
How can natural language processing automate the authoring process? Discuss with applications.
Explain any two of the following a) Shallow parsing b) Transducers for lexicon and rules c) Dictionary and Thesaurus d) Man-Machine Interfaces
