CMU Multilingual NLP 2022 - Data-Driven Strategies for NMT

CMU Multilingual NLP 2022 - Data-Driven Strategies for NMT

Graham Neubig via YouTube Direct link

Dictionarybased augmentation

25 of 29

25 of 29

Dictionarybased augmentation

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

CMU Multilingual NLP 2022 - Data-Driven Strategies for NMT

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

  1. 1 Introduction
  2. 2 Machine Translation Evaluation
  3. 3 Manual Evaluation
  4. 4 Human Evaluation Shared Tasks
  5. 5 Blue Scores
  6. 6 Shortness Penalty
  7. 7 Bert Score
  8. 8 BlueRT
  9. 9 Comet
  10. 10 Bart Score
  11. 11 Meta Evaluation
  12. 12 Database Strategies
  13. 13 High and Low Resource Languages
  14. 14 Data Augmentation
  15. 15 Back Translation
  16. 16 Training Schedule
  17. 17 Generating Translations
  18. 18 In iterative back translation
  19. 19 Metaback translation
  20. 20 Metaback translation issues
  21. 21 High resource languages augmentation
  22. 22 High resource languages pivoting
  23. 23 Monolingual data copying
  24. 24 Transfer learning
  25. 25 Dictionarybased augmentation
  26. 26 Word alignment
  27. 27 Word by word data augmentation
  28. 28 Reordering
  29. 29 Assignment

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.