Teaching Machines Through Human Explanations

Teaching Machines Through Human Explanations

Open Data Science via YouTube Direct link

Intro

1 of 19

1 of 19

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Teaching Machines Through Human Explanations

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

  1. 1 Intro
  2. 2 A Surprisingly "Simple" Recipe for Modern NLP
  3. 3 Cost of data labeling: relation extraction
  4. 4 Cost of data labeling: more complex task
  5. 5 Workaround for (less) data labeling?
  6. 6 How "labels" alone could make things wrong
  7. 7 From "labels" to "explanations of labels" One explanation generalizes to many examples
  8. 8 Learning from Human Explanation
  9. 9 Our Focus: Natural Language Explanations
  10. 10 Learning with Human Explanations
  11. 11 Explanations to "labeling rules"
  12. 12 Generalizing explanations Matching labeling rules to create pseudo labeled data
  13. 13 Challenge: Language Variations
  14. 14 Neural Rule Grounding for rule generalization
  15. 15 A Learable, Soft Rule Matching Function
  16. 16 Neural Execution Tree (NEXT) for Soft Matching
  17. 17 Study on Label Efficiency (TACRED)
  18. 18 Results: Hate Speech (Binary) Classification
  19. 19 Take-aways . "One explanation generalizes to many examples" - better label efficiency vs. conventional supervision

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.