Scribd
Upload
29 views3 pages

Unit 123 (NLP)

The document outlines key concepts in Natural Language Processing (NLP), including the significance of syntactic, semantic, and pragmatic knowledge, and the distinction between Natural Language Understanding (NLU) and Natural Language Generation (NLG). It also addresses ambiguity in natural language, various issues in NLP, and details on morphology, parsing techniques, and the differences between rule-based and probabilistic parsing. Additionally, it discusses the impact of hybrid parsing models and stochastic tagging in NLP applications.

Uploaded by

terameravlog912
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
29 views3 pages

Unit 123 (NLP)

The document outlines key concepts in Natural Language Processing (NLP), including the significance of syntactic, semantic, and pragmatic knowledge, and the distinction between Natural Language Understanding (NLU) and Natural Language Generation (NLG). It also addresses ambiguity in natural language, various issues in NLP, and details on morphology, parsing techniques, and the differences between rule-based and probabilistic parsing. Additionally, it discusses the impact of hybrid parsing models and stochastic tagging in NLP applications.

Uploaded by

terameravlog912
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Unit-1

1. Explain the importance of different forms of knowledge such as syntactic, semantic, and pragmatic
knowledge in enhancing the performance and accuracy of Natural Language Processing (NLP)
systems.
2. Distinguish between Natural Language Understanding (NLU) and Natural Language Generation
(NLG) in terms of their functions and applications within the field of Natural Language Processing
(NLP).
3. Explain Ambiguity in Natural language and discuss the different types of ambiguity.
4. What are the various issues in natural language processing? Explain

Unit-2

1.Discuss Inflectional morphology & Derivational morphology, with suitable example.

2. Draw parse tree for following English statements:

1. Book that Drama.

2.. Nayna pick up the doll.


3.Discuss why Morphemes are considered as building blocks of morphology. Categorize free morphemes in
linguistics.

5. What do you understand by N-grams? Give Explanation


6. What is Parsing? Give detailed description about Top down parsing.

Unit-3
1.Given the sentence "I saw the man with the telescope", apply parsing techniques to identify the
different syntactic structures.
2. Evaluate the impact of hybrid parsing models on NLP applications such as chatbots and search
engines.
3. Explain how probabilistic parsing differs from rule-based parsing.
Probabilistic parsing and rule-based parsing are two different approaches used in Natural
Language Processing (NLP) for syntactic analysis of sentences.

Rule-Based Parsing
 Uses predefined grammar rules: It relies on handcrafted grammatical rules (such as
Context-Free Grammar (CFG)) to parse sentences.
 Strict and deterministic: The parser follows a fixed set of rules to analyze the
structure of a sentence.
 Example Approach: A top-down or bottom-up parser that applies syntactic rules to
build a parse tree.
 Limitation: Struggles with ambiguity (where multiple interpretations exist) and is
less effective for real-world noisy text.

S → NP VP
NP → Det N
VP → V NP
Det → "the"
N → "cat"
V → "chased"

2. Probabilistic Parsing (Statistical Parsing)

 Uses probability models: Instead of fixed rules, it assigns probabilities to different


parse trees based on corpus data.
 Handles ambiguity better: It ranks possible parses and chooses the most probable
one.
 Example Approach: Probabilistic Context-Free Grammar (PCFG), where each
rule has an associated probability learned from training data.
 Limitation: Requires a large annotated dataset (treebanks) for training.

4. Discuss stochastic tagging.

You might also like