NATURAL LANGUAGE PROCESSING

Paper Code: 
24MCA423D
Credits: 
02
Periods/week: 
02
Max. Marks: 
100.00
Objective: 

This course enables the students to

  • Develop an understanding for structures and challenges in natural language.
  • Learn various techniques under Natural Language Processing (NLP) to solve language processing problems.
  • Develop competency to use NLTK in Python

 

Course Outcomes: 

Course

Learning Outcome (at course level)

 

Learning and teaching strategies

Assessment Strategies

Course Code

Course

Title

24MCA 423D

Natural Language Processing

(Theory)

  1. Analyse basic structure of natural language and Process text by using NLP techniques.
  2. Classify Grammer and sentence structure for NLP.
  3. Demonstrate use of Language models and Part of Speech Tagger.
  4. Examine use of NLTK for processing text.
  5. Discuss neural network models for NLP applications.
  6. Contribute effectively in course-specific interaction

Approach in teaching:

Interactive Lectures, Discussion, Presentations, Video Tutorials, Demonstration.

 

Learning activities for the students:

Self-learning Assignments, Effective questions, Simulation

  • Assignments
  • Written test in classroom
  • Classroom Activity
  • Continuous Assessment
  • Semester End Examination

 

12.00
Unit I: 

Introduction to Natural Language Processing:

Natural Language Processing: Need, applications, Challenges in NLP: Ambiguity in language, Contextual words and phrases and homonyms, Co-reference, Domain-specific language, Low-resource languages, Segmentation, Lemmatization, Spelling correction, Synsets, Hypernyms and Code mixed language. Computational Linguistics, Different levels of Language Analysis, Representations and Understanding, Organization of Natural language Understanding Systems, Tokenization, Stop Words.

 

12.00
Unit II: 

Grammar for Natural Language:

Grammar and sentence Structure, Top-Down and Bottom-Up Parsers, Transition Network Grammars, Auxiliary Verbs and Verb Phrases, Movement Phenomenon in Language, Context-Free Grammer, Handling questions in Context-Free Grammars. Human preferences in Parsing, Encoding uncertainty, Deterministic Parser.

 

12.00
Unit III: 

Language Modeling and POS Tagging

Introduction to N-grams, Chain Rule, Smoothing –Interpolation, Backoff, Web-Scale LMs, Evaluation and Perplexity.

Hidden Markov Models and POS Tagging: Part of Speech Tagging, Markov Chain, Hidden Markov Models, Forward Algorithm, Viterbi Algorithm

 

12.00
Unit IV: 

Introduction to Natural Language Tool Kit (NLTK) with Python:

Text normalization, Tokenizing, Filtering Stop Words, Stemming, Tagging, Word representation, Sentence representation, Vector space model, Term Frequency, TF-IDF Representation, Introduction to Word embedding, iNLTK (Natural Language Toolkit for Indic Languages).

 

12.00
Unit V: 

Neural Networks for Text

Multi Layer Perceptron, Convolutional Neural Network, Recursive Neural Network, Recurrent Neural Network, Long Short-Term Memory (LSTM), Sequence to sequence modeling, Text classification using neural network. Introduction to Machine translation, Natural Language Generation, Large language  models , Question Answering Bot, Generative models, Generative Pre-Trained Transformer (GPT).

 

ESSENTIAL READINGS: 
  1. L. M. Ivansca, S. C. Shapiro, “Natural Language Processing and Language Representation”, AAAI Press, 2000
  2. Speech and Language Processing, Jurafsky and Martin, Pearson Education.
  3. Tanveer Siddiqui, US Tiwary, Natural Language Processing and Information Retrieval, Oxford University Press, 2008.
  4. Steven Bird, Ewan Klein, and Edward Loper, ‘Natural Language Processing with Python’, O'rielly, https://www.nltk.org/book/.

 

REFERENCES: 
  1. Christopher D. Manning and Hinrich Schutze, “Foundations of Statistical Natural Language Processing”, MIT Press, 1999.
  2. Daniel and James H. Martin “Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition”, Second Edition, Prentice Hall of India, 2008.
  3. James Allen, “Natural Language Processing with Python”, First Edition, O’Reilly Media, 2009.

E-Resources

  1. NLP and Deep Learning at github repository (https://github.com/UKPLab/deeplearning4nlp-tutorial)
  2. Introduction to NLP (Free Certification from Great Learning)
  3. https://www.mygreatlearning.com/academy/learn-for-free/courses/introduction-to-natural-language-processing

Journals

  1. Natural Language Processing Journal, ScienceDirect
  2. Natural Language Processing (NLP) and Applications, MDPI
  3. Journal for Language Technology and Computational Linguistics
  4. International Journal Of Natural Language Processing (IJNLP)

 

 

Academic Year: 
2024-25
  • Printer-friendly version