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

Section A – Basic Concept Questions (Description)

Section A contains short conceptual questions related to the fundamental concepts of Natural Language Processing (NLP). Students are required to provide short definitions or explanations of important linguistic and computational concepts used in NLP systems.

The questions in this section focus on topics such as issues and challenges in NLP, lexicons, parsing techniques, speech understanding systems, and ambiguity in natural language. Students must understand how natural language differs from formal languages and why it is difficult for computers to process human language.

Important linguistic concepts such as syntax, semantics, probabilistic context-free grammars (PCFG), and stochastic part-of-speech tagging are also included. These concepts help machines analyze and interpret human language.

Students must also understand the elements of a language, which include phonology, morphology, syntax, semantics, and pragmatics.

The objective of this section is to evaluate the student’s understanding of basic NLP terminology and linguistic foundations used in language processing systems.

Questions for Section A

What are the issues and problems in Natural Language Processing?

What is a lexicon in NLP?

What are the advantages of a speech understanding system?

Explain left associative grammars.

What is best-first parsing?

Explain the scope of ambiguity in natural languages.

Differentiate between syntax and semantics.

What are probabilistic context-free grammars?

What is stochastic part-of-speech tagging?

What are the elements of a language?

Section B – Descriptive Questions (Description)

Section B includes descriptive questions that require detailed explanations of NLP system architecture, parsing techniques, and language analysis methods.

Students must understand how NLP systems are evaluated, including accuracy, performance, and linguistic correctness. Evaluation is important to measure how well NLP systems perform tasks such as machine translation or text analysis.

Another important concept covered in this section is the difference between Natural Language Processing (NLP) and Natural Language Understanding (NLU). While NLP focuses on processing text data, NLU focuses on interpreting the meaning of language.

Students must also explain why processing natural languages is difficult, due to factors such as ambiguity, context dependency, and variability in human language.

The section also includes questions about parsing techniques, which help analyze the grammatical structure of sentences. Students must understand different parsing approaches used in NLP systems.

Another important topic is the different levels of language analysis, which include lexical analysis, syntactic analysis, semantic analysis, discourse analysis, and pragmatic analysis.

Students may also be asked to explain the organization of NLP systems, speech dialogue systems, and human–machine interfaces designed using NLP technologies.

Questions for Section B

How are Natural Language Processing systems evaluated? Explain.

Differentiate between Natural Language Processing (NLP) and Natural Language Understanding (NLU).

Why is natural language processing needed? Why is it difficult to process human languages?

What are the issues in parsing? Explain different parsing techniques with examples.

Explain the different levels of language analysis in NLP systems.

Explain the organization and structure of NLP systems.

How can speech dialogue systems reduce errors caused by incorrect speech recognition?

Explain how man–machine interfaces are designed using NLP techniques.

Section C – Long Analytical Questions (Description)

Section C contains long analytical questions that require deeper understanding of knowledge representation and grammar transformation techniques used in NLP systems.

One important topic in this section is semantic networks, which are used to represent knowledge in NLP systems. Semantic networks represent concepts as nodes and relationships as connections between them. Students must explain how information can be inferred from these networks.

Another important topic is word-based NLP systems, where systems analyze individual words without considering their context. Students must explain how such systems work and what lexical knowledge they require.

The section also includes questions about context-free grammar (CFG) transformation into Chomsky Normal Form (CNF). Students must write algorithms for converting CFG into CNF and explain the process with examples.

These topics help students understand knowledge representation, language structure processing, and grammar-based language analysis in NLP systems.

Questions for Section C

Explain how knowledge is represented using semantic networks and how information is inferred from them.

Give an example of an NLP system that analyzes individual words without context. Explain how it works.

Write an algorithm to convert a context-free grammar into Chomsky Normal Form and explain it with examples.