From Paper to Product - How We Implemented BERT

From Paper to Product - How We Implemented BERT

MLCon | Machine Learning Conference via YouTube Direct link

ZukaText

36 of 37

36 of 37

ZukaText

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

From Paper to Product - How We Implemented BERT

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

  1. 1 Introduction
  2. 2 About the talk
  3. 3 How did it start
  4. 4 What happens when the customer is waited
  5. 5 Good old AI
  6. 6 Visionary
  7. 7 English
  8. 8 German
  9. 9 Product
  10. 10 Customer Feedback
  11. 11 Part of Speech Tagging
  12. 12 Architecture
  13. 13 Stanford NLP
  14. 14 Reinventing the wheel
  15. 15 What is BERT
  16. 16 What is supervised training
  17. 17 Unsupervised learning
  18. 18 Unsupervised training
  19. 19 Semisupervised training
  20. 20 Input structure
  21. 21 Transformer block
  22. 22 What is good
  23. 23 What is bad
  24. 24 How did we do it
  25. 25 BERT parameter tuning
  26. 26 Preprocessing
  27. 27 Word pieces
  28. 28 Morphemes vs morphs
  29. 29 Dictionary size
  30. 30 How does it look
  31. 31 What did we save
  32. 32 Training
  33. 33 Training Results
  34. 34 Future Plans
  35. 35 Backend
  36. 36 ZukaText
  37. 37 Whats next

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.