Improving Natural Language Understanding Through Adversarial Testing

Improving Natural Language Understanding Through Adversarial Testing

Stanford Online via YouTube Direct link

Intro

1 of 26

1 of 26

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Improving Natural Language Understanding Through Adversarial Testing

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

  1. 1 Intro
  2. 2 Overview
  3. 3 Image captioning
  4. 4 Watson wins Jeopardy (2011)
  5. 5 Natural Language Inference (NLI)
  6. 6 Stanford Natural Language Inference (SNLI)
  7. 7 "Superhuman" performance on other tasks
  8. 8 The promise of artificial assistants
  9. 9 Two perspectives
  10. 10 Standard evaluations
  11. 11 Adversarial evaluations
  12. 12 NLI adversarial testing
  13. 13 ROBERTa evaluation
  14. 14 Adversarial NLI
  15. 15 High-level summary
  16. 16 Assignments and bake-offs
  17. 17 Assign/Bake-off: Word-level entailment
  18. 18 Assign/Bake-off: Contextual color describers
  19. 19 Wrap-up
  20. 20 Key Motivations
  21. 21 Literature Review to Project
  22. 22 Experiment Flow
  23. 23 Results and Analysis
  24. 24 Conclusions
  25. 25 Lessons Learned
  26. 26 Thank you

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.