Announcements
• Join MS Teams with code: be1n1vl (Login to MS Teams using IITB LDAP)
•
Access course lecture recordings on
YouTube channel
Subscribe
Course Details
CS772: Deep Learning for Natural Language Processing (Autumn, 2025)
Department of Computer Science and Engineering
Indian Institute of Technology Bombay
Time Table and Venue
- Slot: 11
- Venue: CC103 (First 4 Classes at FC Kohli)
- Tuesday: 3:30 PM to 5 PM
- Friday: 3:30 PM to 5 PM
Motivation
Deep Learning (DL) is a framework for solving AI problems based on a network of neurons organized in many layers. DL has found heavy use in Natural Language Processing (NLP) too, including problems like machine translation, sentiment and emotion analysis, question answering, information extraction, and so on, improving performance on automatic systems by orders of magnitude.
The course CS626 (Speech, NLP, and the Web) being taught in the the CSE Department at IIT Bombay for the last several years creates a strong foundation in NLP, covering the whole NLP stack, starting from morphology to part of speech tagging, to parsing and discourse and pragmatics. Students of this course acquire a strong grip on tasks, techniques, and linguistics of a plethora of NLP problems. Past lectures of CS626 can be found here
CS772 (Deep Learning for Natural Language Processing) comes as a natural sequel to CS626. Language tasks are examined through the lens of Deep Learning. Foundations and advancements in Deep Learning are taught, integrated with NLP problems. For example, sequence-to-sequence transformers are covered with applications in machine translation. Similarly, various techniques in word embedding are taught with applications to text classification, information extraction, etc. Recent breakthroughs such as those involving Large Language Models (LLMs) and Generative AI (GenAI) are also highlighted as natural extensions of these core concepts. Throughout the course, references and allusions will be made to LLMs and GenAI.
Course Description
- Background: History of Neural Nets; History of NLP; Basic Mathematical Machinery - Linear Algebra, Probability, Information Theory, etc.; Basic Linguistic Machinery - Phonology, morphology, syntax, semantics.
- Introducing Neural Computation: Perceptrons, Feedforward Neural Network and Backpropagation, Recurrent Neural Nets.
- Difference between Classical Machine Learning and Deep Learning: Representation - Symbolic Representation, Distributed Representation, Compositionality; Parametric and non-parametric learning.
- Word Embeddings: Word2Vec (CBOW and Skip Gram), Glove, FastText.
- Application of Word Embedding to Shallow Parsing: Morphological Processing, Part of Speech Tagging and Chunking.
- Sequence to Sequence (seq2seq) Transformation using Deep Learning: LSTMs and Variants, Attention, Transformers.
- Transformer: Architecture and Functioning, Attention, Positional Encoding, Layer Normalization, Applications in Sentiment Analysis, Image Labelling etc.
- Deep Neural Net based Language Modeling: XLM, BERT, GPT2-3 etc.; Subword Modeling; Transfer Learning and Multilingual Modeling.
- Small LM, Medium LM and Large LM: Language Modelling, Statistical Language Modelling; Curse of Dimensionality, Neural Language Modelling, Various LMs like BERT, XLM, etc., Open LLMs like Llama, Mistral, Mixtral.
- Pretraining and Finetuning: RAG, Generative Pretraining and GPT series; Transfer Learning and 0-shot Learning, Finetuning and few-shot learning; domain and language adaptation, Knowledge Graph Embedding; Knowledge Infusion; Retrieval Augmented Generation Natural Language Generation.
- Application of seq2seq in Machine Translation: Supervised, Semi-supervised, and Unsupervised MT; Encoder-Decoder and Attention in MT; Memory Networks in MT.
- Deep Learning and Deep Parsing: Recursive Neural Nets; Neural Constituency Parsing; Neural Dependency Parsing.
- Deep Learning and Deep Semantics: Word Embeddings and Word Sense Disambiguation; Semantic Role Labeling with Neural Nets.
- Neural Text Classification: Sentiment and Emotion labeling with Deep Neural Nets (DNN); DNN-based Question Answering.
- The indispensability of DNN in Multimodal NLP: Advanced Problems like Sarcasm, Metaphor, Humor, and Fake News Detection using multimodality and DNN.
- Natural Language Generation: Extractive and Abstractive Summarization with Neural Nets.
- Large Language Models and Generative AI: Llama3 like systems, ChatGPT, Gemini, Copilot, Comet etc.
- Good and Bad LLMs: Bias, Hallucination, FakeNews detection and mitigation.
References
- Pushpak Bhattacharyya and Aditya Madhav Joshi, Natural Language Processing, Print ISBN: 978-93-5746-283-9 eISBN: 978-93-5746-239-6, Wiley, 2023.
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016.
- Dan Jurafsky and James Martin, Speech and Language Processing, 3rd Edition, October 16, 2019.Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola, Dive into Deep Learning, e-book, 2020.
- Christopher Manning and Heinrich Schutze, Foundations of Statistical Natural Language Processing, MIT Press, 1999.
- Daniel Graupe, Deep Learning Neural Networks: Design and Case Studies, World Scientific Publishing Co., Inc., 2016.
- Pushpak Bhattacharyya, Machine Translation, CRC Press, 2017.
- Journals: Computational Linguistics, Natural Language Engineering, Journal of Machine Learning Research (JMLR), Neural Computation, IEEE Transactions on Neural Networks and Learning Systems.
- Conferences: Annual Meeting of the Association of Computational Linguistics (ACL), Neural Information Processing (NeuiPS), Int’l Conf on Machine Learning (ICML), Empirical Methods in NLP (EMNLP).
Pre-requisites
- Python (or similar language) Programming skill
- Basics of Statistics and Probability
- Basics of Linear Algebra
- Basics of Machine Learning
Course Instructor
Teaching Assistants
Course Materials
| Lecture | Topics | Slide Links | Video Links |
|---|---|---|---|
| Week 1 (Week of 28th July) |
|
Week 1 (T)
Week 1 (F) |
Lecture 1 Lecture 2 |
| Week 2 (Week of 4th Aug) |
|
-----
Week 2 (F) |
----- Lecture 3 |
| Week 3 (Week of 11th Aug) |
|
Week 3 (T)
----- |
Lecture 4
----- |
| Week 4 (Week of 18th Aug) |
|
Week 4 (T)
Week 4 (F) |
Lecture 5
Lecture 6 |
| Week 5 (Week of 25th Aug) |
|
Week 5 (T)
Week 5 (F) |
Lecture 7
Lecture 8 |
| Week 6 (Week of 1st Sept) |
|
Week 6 (T)
Week 6 (F) |
Lecture 9
Lecture 10 |
| Week 7 (Week of 8th Sept) |
|
Week 7 (T)
|
Lecture 11
|
| Week 8 (Week of 15th Sept) |
|
----
|
----
|
| Week 9 (Week of 22nd Sept) |
|
Week 9 (T) Code accompanying the slides Code for the tutorial Week 9 (F) |
Lecture 12
Lecture 13 |
| Week 10 (Week of 29nd Sept) |
|
Week 10 (T) Week 10 (F) |
Lecture 14
Lecture 15 |
| Week 11 (Week of 6th Oct) |
|
---- Week 11 (F) |
----
Lecture 16 |
| Week 12 (Week of 13th Oct) |
|
Week 12 (T) Week 12 (F) |
Lecture 17
Lecture 18 |
| Week 13 (Week of 20th Oct) |
|
Week 13 (T) Week 13 (F) |
Lecture 19
Lecture 20 |
| Week 14 (Week of 27th Oct) |
|
Week 14 (T) and (F) |
Lecture 21
Lecture 22 |
| Week 15 (Week of 3rd Nov) |
|
Week 15 (T) Week 15 (F) |
Lecture 23
Lecture 24 |
Contact Us
- CFILT Lab
- Room Number: 401, 4th Floor, new CC building
- Department of Computer Science and Engineering
- Indian Institute of Technology Bombay
- Mumbai 400076, India