THEORY EXAMINATION (SEM–VIII) 2016-17 NATURAL LANGUAGE PROCESSING

B.Tech General 0 downloads

₹29.00

Section A – Basic Concept Questions (Description)

Section A contains short conceptual questions that test the basic understanding of Natural Language Processing (NLP). Students are required to provide brief definitions and explanations of important NLP concepts related to language understanding, linguistic structures, and machine translation.

The topics covered in this section include semantics, language modeling, part-of-speech tagging, machine translation, and grammar structures. Students must also understand the role of human assistance in improving machine translation systems and how linguistic concepts such as conceptual tenses are used in NLP models.

Another important topic is the difference between left associative grammars and ambiguous grammars, which are used in syntactic analysis. The section also includes questions about the major tasks of NLP, such as language understanding, language generation, and information extraction.

The main objective of this section is to test the student’s knowledge of basic terminology and foundational concepts used in natural language processing systems.

Questions for Section A

What is meant by the semantics of a natural language utterance?

What is language modeling in NLP?

What are the major tasks of Natural Language Processing?

Why did RSST have a greater influence on Natural Language Generation (NLG)?

Differentiate between left associative grammar and ambiguous grammar.

How can humans help improve machine translation systems?

List the conceptual tenses proposed by Schank.

What is part-of-speech tagging? Give an example.

What is machine translation? Explain with an example.

List the major tasks of NLP.

Section B – Descriptive Questions (Description)

Section B includes descriptive and analytical questions related to algorithms, parsing techniques, and machine learning methods used in natural language processing.

Students may be asked to write algorithms such as finite-state transducer parsing algorithms and explain how these algorithms process language data. These algorithms are important for building language processing systems that can recognize patterns in text.

Another important topic is machine learning methods used in language translation, where students must explain techniques such as statistical machine translation and rule-based machine translation.

Students must also understand semantic graph models and optimization techniques, which help represent the meaning of sentences in NLP systems.

The section also includes questions related to context-free grammar conversion into Chomsky Normal Form, parsing strategies such as top-down and bottom-up parsing, and advanced parsing frameworks like Augmented Transition Networks (ATN).

Students may also be asked to explain how movement phenomena in language affect NLP systems and how interpretation mechanisms are used to understand natural language.

Questions for Section B

Write an algorithm for parsing a finite-state transducer and explain it with an example.

Explain machine learning methods used in language translation.

Describe graph models and optimization techniques used in semantics.

Explain how to convert a context-free grammar into Chomsky Normal Form.

Compare top-down and bottom-up parsing approaches.

Explain Augmented Transition Networks with an example.

How does the movement phenomenon affect NLP systems?

Explain the role of language interpretation in NLP systems.

Section C – Long Analytical Questions (Description)

Section C includes long analytical questions that require deeper understanding of linguistic theories, NLP system evaluation, and real-world applications of natural language processing.

One of the main topics in this section is evaluation of language understanding systems, where students must explain how NLP systems are tested for accuracy, efficiency, and linguistic correctness.

Another important concept is linguistic analysis, including terms such as lexicon and morpheme, which are fundamental units of language used in computational linguistics.

Students must also understand the Chomsky hierarchy, which classifies formal grammars into different types used in computational linguistics and automata theory.

The section also covers applications and commercial uses of NLP, including machine translation, speech recognition, chatbots, sentiment analysis, and information retrieval.

Students may also be asked to write short notes on topics such as semantics and pragmatics, probabilistic context-free grammars, ambiguity resolution, and different levels of language analysis.