Continuous State Machines and Grammars for Linguistic Structure Prediction

Continuous State Machines and Grammars for Linguistic Structure Prediction

Simons Institute via YouTube Direct link

Better Dependency Parsers?

20 of 23

20 of 23

Better Dependency Parsers?

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Continuous State Machines and Grammars for Linguistic Structure Prediction

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

  1. 1 Intro
  2. 2 Linguistic Structure Example: Dependencies
  3. 3 "Global" or "Graph-Based" Paradigm
  4. 4 Greedy Parsing with a Stack
  5. 5 Recurrent Neural Network
  6. 6 Stack RNN
  7. 7 Stack LSTM Parser
  8. 8 Token and Tree Representations
  9. 9 Learning
  10. 10 Results (Labeled Attachment Score)
  11. 11 Variations
  12. 12 Vanation: Many Languages, One Parser (Ammar et al., TACL 2016)
  13. 13 Stack LSTM MALOPA
  14. 14 Tiny Target Treebank: Results
  15. 15 Zero Target Treebank: Results
  16. 16 Variation: Add Semantics (Swayamcipta et al., CONLL 2016)
  17. 17 Linguistic Structure Example: Semantic Dependencies
  18. 18 Variation: RNN Grammars (Dyer et al., NAACL 2016, Kuncoro et al., EACL 2017)
  19. 19 Another Linguistic Structure Example: Phrase-Structure Tree
  20. 20 Better Dependency Parsers?
  21. 21 Tree & String Generation with a Stack
  22. 22 Additional Details
  23. 23 Conclusions

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.