Language Learning in Humans and Machines - Making Connections to Make Progress

Language Learning in Humans and Machines - Making Connections to Make Progress

Alan Turing Institute via YouTube Direct link

Intro

1 of 35

1 of 35

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Language Learning in Humans and Machines - Making Connections to Make Progress

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Today's talk
  3. 3 Interpreting a sentence
  4. 4 The real situation
  5. 5 Other examples of ambiguity
  6. 6 Labelled examples
  7. 7 Extracting features
  8. 8 Statistical natural language processing
  9. 9 Labelled data is hard to obtain
  10. 10 Result: unequal access
  11. 11 Human language learning
  12. 12 Must computers learn like humans?
  13. 13 But language isn't "in the world"
  14. 14 Research programme
  15. 15 Learning biases
  16. 16 Stronger bias = less data
  17. 17 Example problem: segmentation
  18. 18 Word segmentation
  19. 19 Statistical learning experiment
  20. 20 Testing for learning
  21. 21 How do they do it?
  22. 22 What about real language?
  23. 23 Another strategy
  24. 24 A model for segmenting words
  25. 25 The right bias can help
  26. 26 The Dirichlet process model
  27. 27 Output of the system
  28. 28 Words aren't marbles
  29. 29 Improved system
  30. 30 Where else can these ideas help?
  31. 31 Continuing work
  32. 32 Meaning as translation
  33. 33 Results so far
  34. 34 Conclusions
  35. 35 Acknowledgements

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.