Artificial Intelligence & Data Science is coming soon

We're still writing and reviewing the notes for every subject, and we'll open it when every subject is ready. Meanwhile you can practise aptitude, ask Aria about any subject, or see the branches that are ready.

Artificial Intelligence & Data Science

Natural Language Processing

Grammars and morphology, text representation, n-grams and HMMs, NLP tasks, attention, transformers and BERT.

Interview questions
Notes for Natural Language Processing are being written and reviewed. Until they're up, Aria teaches every topic — ask for any part of the syllabus, with worked numericals.

Coming next in Natural Language Processing

  1. Levels and challenges of NLP· notes coming
  2. Regular expressions and finite automata· notes coming
  3. Context-free grammars· notes coming
  4. Morphology and finite-state transducers· notes coming
  5. Minimum edit distance· notes coming
  6. Corpora and annotation· notes coming
  7. Tokenisation and normalisation· notes coming
  8. Stemming and lemmatisation· notes coming
  9. Subword tokenisation· notes coming
  10. Word representations· notes coming
  11. WordNet· notes coming
  12. N-gram language models· notes coming
  13. Perplexity and smoothing· notes coming
  14. Naive Bayes text classification· notes coming
  15. Hidden Markov models· notes coming
  16. Viterbi algorithm· notes coming
  17. Probabilistic context-free grammars· notes coming
  18. POS tagging· notes coming
  19. Named entity recognition· notes coming
  20. Dependency parsing· notes coming
  21. Evaluation: BLEU and ROUGE· notes coming
  22. Sentiment analysis· notes coming
  23. Word sense disambiguation· notes coming
  24. Attention mechanism· notes coming
  25. Encoder-decoder models· notes coming
  26. Machine translation· notes coming
  27. Transformer architecture· notes coming
  28. BERT· notes coming
  29. Retrieval-augmented generation· notes coming
  30. Morphology of Indian languages· notes coming
  31. Speech production and articulation· notes coming
  32. HMM-based speech recognition· notes coming
  33. Text-to-speech synthesis· notes coming
  34. Earley and CYK parsing· notes coming
  35. Shallow parsing· notes coming
  36. Maximum entropy models and CRFs· notes coming
  37. Indian language wordnets· notes coming
  38. Semantic roles· notes coming
  39. Coreference and anaphora resolution· notes coming
  40. Question answering systems· notes coming
  41. Information retrieval and extraction· notes coming
  42. Textual entailment and cross-lingual retrieval· notes coming
  43. TF-IDF and vector space models· notes coming
  44. Pointwise mutual information· notes coming
  45. Logistic regression for text classification· notes coming
  46. Recurrent neural networks for NLP· notes coming
  47. LSTMs and GRUs for language· notes coming
  48. Fine-tuning pretrained and masked language models· notes coming
  49. Chatbots and text summarisation· notes coming
  50. Probabilistic retrieval and query expansion· notes coming
  51. Relation extraction and open information extraction· notes coming
  52. Natural language generation· notes coming
  53. Discourse: cohesion and reference resolution· notes coming