CS 613: Natural Language Processing

IIT Gandhinagar

Autumn 2025

Instructor: Mayank Singh (email: singh.mayank@iitgn.ac.in)

Office Hours: Always looking for discussions. Just email me for an appointment

Class Schedule: Monday:15:30- 16:50, Thursday: 14:00-15:20

Location: AB 10/202

Communication Google group: cs613-2025.pvtgroup@iitgn.ac.in

Teaching Assistants

1. Himanshu Beniwal (himanshubeniwal@iitgn.ac.in)

2. Sailesh Panda (sailesh.panda@iitgn.ac.in) 

3. Gautham Bharati (gautham.b@iitgn.ac.in)

4. Chetana Dubey (chetana.dubey@iitgn.ac.in)

Prerequisite (Optional)

• Basic Probability & Statistics (ES 331/ MA 202) or equivalent

• Basic understanding of Python programming (ES 102/ ES 112) or equivalent

Course Contents

1. Text processing: Tokenization, Stemming, Spell Correction, etc.

2. Language Modelling: N-grams, smoothing

3. Morphology, Parts of Speech Tagging

4. Syntax: PCFGs, Dependency Parsing

5. Distributional Semantics, Topic Models

6. Lexical Semantics, Word Sense Disambiguation

7. Information Extraction: Relation Extraction, Event Extraction

8. Applications: Text Classification, Sentiment Analysis, Opinion Mining, Summarization

9. Deep Learning for NLP, Representation Learning

Lecture Slides and Additional Materials

• Intro to NLP [Slides]

• Intro to Pytorch [Colab Notebook]

• Basic Data Preprocessing [slides], [script]

• Distributional Semantics [slides] [ Python Notebook]

• Continuous representations [Slides, Word2Vec paper, Parameter Learning, Wevi, Glove Paper]

• Language Modeling [Basics of LM Slides, Smoothing Slides, LM using NLTK, Section 3.8 for relation between entropy, cross-entropy, and perplexity, Good Turing Estimate]

• Neural Language Model [Slides]

• Seq2Seq approach, Attention Mechanism and Transformers [Slides]

• Contextual Word Embeddings, BERT [Slides] 

• GPT Series [Slides], Understanding GPT Implementation [Colab Notebook]

• Tokenization [Slides] [Colab: BPE, Wordpiece]

• Metrics and Benchmarks [Slides]

• Model Quantization [Notes, Recorded Video, Colab Notebook]

Assignments (All deadlines are 11:59 PM IST)

• Assignment - 1

Paper Presentations I

• Team 1 ( Deepdecode ) -  Subliminal Learning: Language models transmit behavioral traits via hidden signals in data  - Video Link 

• Team 2 ( Neural Nexus ) -  ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion  - Video Link 

• Team 3 ( Dropout Squad ) - Pruning via merging: compressing llms via manifold alignment based layer merging - Video Link 

• Team 4 ( IITGnGPT ) - LLM-DetectAIve: a Tool for Fine-Grained Machine-Generated Text Detection - Video Link 

• Team 5 ( Polyglots ) - Bhasha-Abhijnaanam: Native-script and Romanized Language Identification for 22 Indic Languages - Video Link 

• Team 6 ( Lingo Limbos ) - Towards Retrieval-Augmented Architectures for Image Captioning - Video Link 

• Team 7 ( NeuroLingo ) - A Simple Recipe for Multilingual Grammatical Error Correction - Video Link 

• Team 8 ( LexicoGraphers ) - PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages - Video Link 

• Team 9 ( NLPunks ) - Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation - Video Link 

• Team 10 ( Context Bandits ) - YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone - Video Link 

• Team 11 ( Articulex ) - M5 – A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks - Video Link 

• Team 12 ( Machine minds ) - MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets - Video Link 

• Team 13 ( Smashers ) - Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis - Video Link 

• Team 14 ( AipAGluZ  ) - Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights - Video Link 

Grading Policy & Schedule

• Three Assignments (30%)
  Three assignments (each carrying 10 marks). 

• Three Surprise quizzes (30%)
  Three surprise quizzes of 10% marks each. These quizzes will assess your grasp of the content covered in the class. 

• Exam (20%) [A Sample Paper]
  One exam during the examination I. 

• Paper Presentations (20%)

     Two paper presentations (each carrying 10 marks). 

Books

• [DJ] Daniel Jurafsky and James H. Martin. 2000. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition (1st ed.). Prentice Hall PTR, Upper Saddle River, NJ, USA. (Main Textbook)

• [CH] Christopher D. Manning and Hinrich Schütze. 1999. Foundations of Statistical Natural Language Processing. MIT Press, Cambridge, MA, USA.

• [SEE] Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python (1st ed.). O'Reilly Media, Inc.

• [IYA] Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. The MIT Press.