NATURAL LANGUAGE PROCESSING (Professional Elective – IV) B.Tech. IV Year I Sem. JNTUH R-18

• Explain the challenges of morphological analysis and discuss different morphological models (e.g., rule-based, statistical).

• Analyze a given word and identify its morphemes and morphological structure using one of the discussed models.

• Compare and contrast different methods for text segmentation and document summarization, highlighting their strengths and weaknesses.

• Evaluate the performance of a document parsing system based on relevant metrics like precision, recall, and F1-score.

Unit II: Syntax Analysis

• Explain the role of treebanks in syntactic parsing and describe the process of creating a treebank for a specific language.

• Analyze a sentence and illustrate its parse tree using a formal grammar (e.g., CFG, PCFG).

• Compare and contrast different parsing algorithms (e.g., top-down, bottom-up) and discuss their suitability for various parsing tasks.

• Describe how ambiguity resolution techniques handle cases where a sentence has multiple possible parses.

Unit III: Semantic Parsing

• Explain the difference between syntactic and semantic parsing and the challenges involved in semantic interpretation.

• Discuss different system paradigms for semantic parsing (e.g., rule-based, statistical) and their applications.

• Analyze the concept of word sense ambiguity and explain how word sense systems help resolve it.

• Evaluate the performance of a semantic parsing system by measuring its ability to capture the intended meaning of the text.

Unit IV: Predicate-Argument Structure and Meaning Representation Systems

• Explain the importance of predicate-argument structure in understanding the meaning of a sentence.

• Analyze a sentence and identify its predicates and arguments, describing their semantic roles.

• Discuss different meaning representation systems used in NLP (e.g., semantic networks, frames) and their advantages and disadvantages.

• Explain how software tools like Prolog can be used to represent and reason about meaning in NLP applications.

Unit V: Discourse Processing and Language Modeling

• Describe the phenomenon of discourse cohesion and discuss different techniques for identifying and analyzing coherence in text.

• Explain the concept of reference resolution and discuss how NLP systems address anaphora and deictic references.

• Analyze the components of a language model (e.g., n-grams, smoothing techniques) and explain how it predicts the next word in a sequence.

• Compare and contrast different types of language models (e.g., statistical, neural) and discuss their performance on various tasks.