CS7.401 Introduction to NLP

Course Logo

Course Overview ↑ Top

Designed for those seeking an introduction, this course covers introductory topics in Natural Language Processing (NLP). It assumes foundational knowledge in mathematics and programming.

Advanced NLP Course Page - M2025


Instructors

Professor MS Manish Shrivastava
Professor MS Parameswari Krishnamurthy

Teaching Assistants

Aparajitha Aparajitha
Saumitra Saumitra
Aaditya Aaditya
Abraham Abraham
Abraham Aryan
Abraham Ayush
Ketaki Bhavya
Druhan Druhan
Ketaki Ketaki
Yajat Yajat

Logistics ↑ Top

All course related annoucements will be made on Moodle.

Teaching Assistant Office Hours

TA Name Office Hours
Aaditya Monday: 14:00 - 15:00 (IREL)
Ketaki Tuesday: 14:00 - 15:00 (MT NLP Lab)
Bhavya Tuesday: 15:30 - 16:30 (MT NLP Lab)
Yajat Tuesday: 18:30 - 19:30 (MT NLP Lab)
Aparajitha Wednesday (After Class): 10:00 - 11:00 (MT NLP Lab)
Druhan Wednesday: 11:30 - 12:30 (MT NLP Lab)
Aryan Thursday 14:00 - 15:00 (IREL)
Abraham Friday: 14:00 - 15:00 (IREL)
Ayush Friday: 15:30 - 16:30 (MTNLP Lab)
Saumitra Saturday: 14:00 - 15:00 (MT NLP Lab)

Course Schedule ↑ Top

>
# Date Topic Section Resources
1 3-Jan-26 Introduction History of NLP
2 7-Jan-26 Intro to Course, Logistics, NLP
3 10-Jan-26 Intro to NLP
4 17-Jan-26 Tokenization Beginnings - Words, Suffix Tree, Frequency(BPE) Morfessor 2.0
Byte Pair Encoding
5 21-Jan-26 LM WordPiece, SentencePiece, Importance of Tokenization WordPiece
SentencePiece
Byte Pair Encoding
6 24-Jan-26 Language Modeling Introduction to Language modeling Language Modeling
LM and smoothing
7 28-Jan-26 Smoothing Smoothing in NLP Kneser-Ney Smoothing
Smoothing
Kneser-Ney Smoothing
Laplace Smoothing
Interpolation
8 31-Jan-26 Embedding Word Vectors Word2vec parameter learning explained
9 4-Feb-26 Word Embeddings - word2vec SVD
10 7-Feb-26 Neural Networks in NLP Neural LM Backpropogation
Backpropagation
Yes you should understand backprop
Neural Networks
Neural LM
11 11-Feb-26 RNN Neural Networks
Gradient Descent
Learning Phrase Representations using RNN Encoder–Decoder for SMT
12 18-Feb-26 LSTM Understanding LSTM
Sequence to Sequence Learning with Neural Networks
13 21-Feb-26 Quiz 1
14 25-Feb-26 Transformers Bi-LSTM, Enc-Dec, Pitfalls, Attention Neural Machine Translation by Jointly Learning to Align and Translate
Attention is all you need
15 7-Mar-26 Transformer Architecture Illustrated Transformer
Self Attention, Transformers
Intro to Transformers
Attention in Transformers
16 11-Mar-26 Transformer Architecture
17 18-Mar-26 Finetuning, Training, Prefix, Adapters, LoRA LoRA: Low Rank Adaptation
Zero Quant
LLM.int8
18 20-Mar-26 Quantization
19 25-Mar-26 Generation Tasks/Decoding
20 28-Mar-26 Transformers models
21 1-Apr-26 Transformers for Tasks
22 4-Apr-26 Quiz 2
23 8-Apr-26 Transformers for Tasks
24 11-Apr-26
25 15-Apr-26 Parsing Statistical Constituency Parsing
Dependency Parsing
26 18-Apr-26 Neural
27 22-Apr-26 TBA
28 25-Apr-26 TBA

Grading and Weightage ↑ Top

Your final grade in this course will be determined by the following components:

Component Weightage
Assignments * 3 5 + 5 + 10 (20%)
Quiz * 2 7.5 + 7.5 (15%)
Project 45%
Final Exam 20%
Total 100%

Due Dates ↑ Top

Important dates for the course:

Component Date
Team Details Submission 17-Jan-26
A1 Release 21-Jan-26
Project Proposals (Interim) 24-Jan-26
Proposal (Interim) Rejection by TAs 26-Jan-26
Project Finalization, Mentor Assignment 31-Jan-26
Proposal (Final) 31-Jan-26
Final Proposal Grades 8-Feb-26
A1 Due 11-Feb-26
A2 Release 12-Feb-26
A1 Grades 21-Feb-26
A2 Due 5-Mar-26
A3 Release 6-Mar-26
Project Mid Submission 8-Mar-26
A2 Grades 15-Mar-26
Project Mid Grades 18-Mar-26
A3 Due 27-Mar-26
Final Project Due 8-Apr-26
A3 Grades 16-Apr-26
Final Project Evals 13-Apr to 19-Apr-26
Final Grade Assignment 6-May-26

Course Projects ↑ Top

The course project is a significant component of this course (45%), providing an opportunity to apply the concepts and techniques learned to a real-world NLP problem. Students will work in teams of 3 or 4 to propose, develop, and present a project. Projects are expected to be at an advanced level. Submission to conferences/workshops is highly encouraged. Read more on research opportunities.

We encourage students to think creatively and explore areas that genuinely interest them.


Component Weightage
Project Outline 5%
Project Mid 15%
Project Final 25%
Total 45%

Project Areas

  • Efficient/Low-Resource Methods
  • Ethics, Fairness, Bias
  • Generation/Language Modeling
  • Interpretability/Explainability
  • Multilingual/Cross-lingual
  • Multimodal
  • NLP Applications
  • Evaluation/Benchmarking
  • Retrieval & Extraction
  • Document Understanding
  • Graph in NLP
  • Human-centered NLP
  • Machine Translation
  • Syntax: Tagging, Chunking and Parsing
  • Sentiment Analysis

Assignments and Project Policies ↑ Top

Late Submission Policy

Assignment and project deadlines are strictly enforced. Late submissions will not be allowed and no extensions will be provided.

Collaboration Policy

Collaboration on assignments is encouraged for discussion of concepts and general approaches, but all submitted answers must be your individual work. For projects, group collaboration is expected, and the contribution of each member should be clearly documented. Any specific collaboration guidelines for individual assignments or projects will be provided with the assignment description.

Consultation and Research Opportunities

Students are highly encouraged to consult with the instructor, teaching assistants and mentors during office hours or by appointment for guidance on assignments, projects, or course topics. If a project developed in this course shows significant potential for a research paper, students may, at their discretion, invite a TA, a mentor or the instructor whose advice substantially benefited the work to be a co-author. This is not a requirement, but an opportunity to acknowledge significant contributions and foster academic collaboration.

Other Resources ↑ Top