Scribd
Upload
6 views2 pages

CM321 NLP Syllabus

The document outlines a Natural Language Processing course, detailing its objectives, outcomes, and content across four units. Key topics include parsing techniques, named entity recognition, machine translation, sentiment analysis, conversational AI, and summarization. Learning resources include a primary textbook and two reference books for further study.

Uploaded by

Greesh
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
6 views2 pages

CM321 NLP Syllabus

The document outlines a Natural Language Processing course, detailing its objectives, outcomes, and content across four units. Key topics include parsing techniques, named entity recognition, machine translation, sentiment analysis, conversational AI, and summarization. Learning resources include a primary textbook and two reference books for further study.

Uploaded by

Greesh
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/ 2

(R-20)

CM321 NATURAL LANGUAGE PROCESSING L P C


3 0 3

Course Objectives:
The main objectives of this course are
1. Understand the Representation and Layers of NLP.
2. Represent the sentences as parse trees and describe NER and its challenges.
3. Use and create sentiment lexicons and Q&A.
4. Describe extractive Summarization in three generations and LLMs.

Course Outcomes:
After successful completion of the course, the students will be able to:
CO 1: Explain the probabilistic formulation of POS tagging and Viterbi decoding.
CO 2: Execute steps in top-down, bottom-up parsing and NER for example sentences.
CO 3: Analyze the semantic analysis, Question Answering of natural language sentences.
CO 4: Distinguish between extractive and abstractive summarization and LLMs.
Course Content:

UNIT I (CO1)
Introduction: Language and Linguistics, Ambiguity and Layers of NLP, Grammar, Probability,
and Data, Generations of NLP.
Representation and NLP: Ambiguity and Representations, Generation 1: Belongingness via
Grammars, Generation 2: Discrete Representational Semantics, Generation 3: Dense
Representations.
Shallow Parsing: Part-of-Speech Tagging, Statistical POS Tagging, Neural POS Tagging,
Chunking.

UNIT II (CO2)
Deep Parsing: Linguistics of Parsing, Algorithmics of Parsing, Constituency Parsing: Rule
Based, Statistical Parsing, Dependency Parsing, Neural Parsing.
Named Entity Recognition: Problem Formulation, Ambiguity in Named Entity Recognition,
Datasets, First Generation: Rule-Based Approaches, Second Generation: Probabilistic
Models, Third Generation: Sentence Representations and Position-Wise Labelling.
Natural Language Inference: Ambiguity in NLI, Problem Formulation, Datasets, First
Generation: Logical Reasoning, Second Generation: Alignment, Third Generation: Neural
Approaches.

UNIT III (CO3)


Machine Translation: Introduction, Rule-Based Machine Translation, Indian Language
Statistical Machine Translation, Phrase-Based Statistical Machine Translation, Factor-Based
Statistical Machine Translation, Cooperative NLP: Pivot-Based Machine Translation,Neural
Machine Translation.
Sentiment Analysis: Problem Statement, Ambiguity for Sentiment Analysis, Lexicons for
Sentiment Analysis, Rule-Based Sentiment Analysis, Statistical Sentiment Analysis,6 Neural
Approaches to Sentiment Analysis, Sentiment Analysis in Different Languages.
Question Answering: Problem Formulation, Ambiguity in Question Answering, Dataset
Creation, Rule-based Q&A, Second Generation, Third Generation.
(R-20)

UNIT IV (CO4)
Conversational AI: Problem Definition, Ambiguity Resolution in Conversational AI, Rule-
Based Approaches to Conversational AI, Statistical Approaches, Neural Approaches.
Summarization: Ambiguity in Text Summarization, Problem Definitions, Early Work,
Summarization Using Machine Learning.
Large Language Models: Background, Ambiguity Resolution, Generative LLMs, Usage of
LLMs.

Learning Resources:

Text Book:

1. Natural Language Processing, Pushpak Bhattacharyya, Aditya Joshi, Wiley, 2023.


Reference Books:
1. Daniel Jurafsky and James H Martin,”Speech and Language Processing: An introduction to
Natural Language Processing, Computational Linguistics and Speech Recognition”, Prentice
Hall, 2nd Edition, 2008
2. 2. C. Manning and H. Schutze, “Foundations of Statistical Natural Language Processing”, MIT
Press. Cambridge, MA: 1999

You might also like