IIT Kharagpur · Engineering

Deep Learning for Natural Language Processing

Prof. Pawan Goyal · 72 free video lectures

Natural Language Processing finds its applications nearly everywhere -- be it Machine Translation,Question answering, Text Summarization, Dialogs, etc. In the last decade, Deep Learning basedmethods have given very good performance across a variety of NLP tasks, and have become a default choice for…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Lecture 01 : Introduction to the Course
  2. Lecture 02 : Text Processing Basics,Tokenization
  3. Lecture 03 : N-gram Language Models: Part 1
  4. Lecture 04 : N-gram Language Models: Part 2
  5. Lecture 05 : NLP Tasks and Paradigms
  6. Tutorial - 1
  7. Lecture 06 : Supervised Learning
  8. Lecture 07 : Shallow Neural Networks
  9. Lecture 08 : Deep Neural Networks
  10. Lecture 09 : Backpropagation
  11. Lecture 10 : Gradient Descent and Initialization
  12. Tutorial - 2
  13. Lecture 11 : Word Representation
  14. Lecture 12 : Learning Word Representation - Part I
  15. Lecture 13 : Learning Word Representation - Part II
  16. Lecture 14 : Word Vectors: Other Extensions
  17. Lecture 15 : Cross-Lingual Representations
  18. Tutorial-3
  19. Lecture 16 : RNN Language Models
  20. Lecture 17 : RNN Applications : Text Generation, Sequence Labeling, Text Classification
  21. Lecture 18 : RNN for Sequence to Sequence
  22. Lecture 19 : Decoding Strategies
  23. Lecture 20 : Better RNN Units : GRU, LSTM
  24. Tutorial - 4
  25. Lecture 21 : Introduction to Transformers
  26. Lecture 22 :Transformers : Part 2
  27. Lecture 23 : Transformers : Part 3
  28. Lecture 24 : Transformers : Part 4
  29. Lecture 25 : Efficient Transformers
  30. Tutorial-5
  31. Lecture 26 : Pretraining
  32. Lecture 27 : Pretraining Transformer Encoder
  33. Lecture 28 : Pretraining Transformer Encoder, Encoder-Decoder
  34. Lecture 29 : Pretraining Transformer Decoder
  35. Lecture 30 : More on Pretraining
  36. Tutorial-6
  37. Lecture 31 : Applications : Question Answering - I
  38. Lecture 32 : Applications : Question Answering - II
  39. Lecture 33 : Applications : Dialogue Systems - I
  40. Lecture 34 : Applications : Dialogue Systems - II
  41. Lecture 35 : Applications : Text Summarization
  42. Tutorial-7
  43. Lecture 36 : Instruction Fine-Tuning-I
  44. Lecture 37 : Instruction Fine-Tuning-II
  45. Lecture 38 : Reinforcement Learning from Human Feedback - I
  46. Lecture 39 : Reinforcement Learning from Human Feedback - II
  47. Lecture 40 : Aligning to User Preferences via Direct Preference Optimization
  48. Tutorial-8
  49. Lecture 41 : Prompting-I
  50. Lecture 42 : Prompting : Why does in-context learning work?
  51. Lecture 43 : Advanced Prompting Techniques
  52. Lecture 44 : Tool-aided Language Models
  53. Lecture 45 : Automatic Prompt Engineering
  54. Tutorial - 9
  55. Lecture 46 : Parameter-efficient fine-tuning - I
  56. Lecture 47 : Parameter-efficient fine-tuning - II
  57. Lecture 48 : Efficient fine-tuning for quantized LMs-I
  58. Lecture 49 : Efficient fine-tuning for quantized LMs-II
  59. Lecture 50 : Other Parameter Efficient Methods: Pruning, Distillation
  60. Tutorial-10
  61. Lecture 51 : Scaling Laws of LLMs
  62. Lecture 52 : Modern LLMs and Architecture Variations - I
  63. Lecture 53 : Modern LLMs and Architecture Variations: Positional Embeddings
  64. Lecture 54 : Long Sequence Modeling
  65. Lecture 55 : Retrieval Augmented Generation
  66. Tutorial-11
  67. Lecture 56 : Model Interpretability
  68. Lecture 57 : Model Interpretability - Multilingual
  69. Lecture 58 : Model Interpretability - III
  70. Lecture 59 : Trustworty LLMs : Taxonomy
  71. Lecture 60 : Trustworty LLMs : Machine Unlearning
  72. Tutorial-12

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IIT Kharagpur.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights