Natural Language Processing

Learning Outcomes: 
Upon Completion of the course, the students will be able to
To Learn natural language processing and to learn how to apply basic algorithms in this field.
To get acquainted with the algorithmic description of the main language levels: morphology, syntax, semantics, pragmatics, discourse as well as the resources of natural language data – corpora
Syllabus: 
Unit NoTopics
1

Introducing to Natural Language Processing

Rationalist and Empiricist Approaches to Language,  Scientific Content,  The Ambiguity of Language: Why NLP Is Difficult,    

2

Regular Expression and Automata

Regular Expressions, Finite-State Automata, Regular Languages and FSAs  

3

NLP Applications and Text Summary

Semantic Similarity, Thesaurus based word similarity methods, Vector Space Model, Dimensionality Reduction, NLP Applications 

4

Context-Free Grammars and Parsing with Context-Free Grammars

Syntax, Parsing, Various parsing methods, Penn Treebank, statistical parsing, lexicalized parsing, Dependency Parcing

5

Probabilistic Models of Pronunciation and Spelling

Dealing with Spelling Errors, Spelling Error Patterns, Detecting Non-Word Errors,  Probabilistic Models, Applying the Bayesian method to spelling, Minimum Edit Distance

6

Language Modeling

N-gram Models, Maximum Likelihood Estimation, Smoothing, Backoff, Interpolation, Evaluation of LM: Perplexity & Word Error Rate, Issues with language models and solutions, Word Sense Disambiguation

7

Markov Models and Part of Speech Tagging

Noisy Channel Model, Part of Speech Tagging, Hidden Markov Model, Statistical POS tagging, Transformation-Based Tagging

8

Text Summarization

Summarization, Summarization Techniques, Summarization Evaluation, Sentence Simplification

9

Collocations and Information Retrieval

Collocations, Introduction to Information Retrieval, Evaluation of IR, Text Classification, Text Clustering, IR toolkits

10

Text Categorization

Decision Trees, Maximum Entropy Modelling, Perceptrons, k Nearest Neighbor Classification

Text Books: 
Name : 
Speech and language processing: An introduction to natural language processing
Author: 
Jurafsky, D.
Name : 
Foundations of statistical natural language processing. Vol. 999
Author: 
Manning, Christopher D.,
HinrichSchütz
Publication: 
MIT
Name : 
Natural language processing with Python: analyzing text with the natural language toolkit.
Author: 
Bird, S., Klein,
Loper,
Publication: 
O'Reilly
Syllabus PDF: 
AttachmentSize
PDF icon NLP.pdf312.46 KB
branch: 
BDA
Course: 
2018
Stream: 
B.Tech