The Meaning and Measurement of Bias - Lessons from NLP

The Meaning and Measurement of Bias - Lessons from NLP

ACM FAccT Conference via YouTube Direct link

Recidivism

10 of 17

10 of 17

Recidivism

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

The Meaning and Measurement of Bias - Lessons from NLP

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

  1. 1 Intro
  2. 2 Things we care about
  3. 3 The measurement process
  4. 4 Cartoon of a ML pipeline
  5. 5 This tutorial We introduce the language and the tools of construct validity
  6. 6 Measuring height
  7. 7 Measuring socioeconomic status using income
  8. 8 Measuring topics using word counts
  9. 9 Evaluating measurement models
  10. 10 Recidivism
  11. 11 Fairness is an unobserved theoretical construct
  12. 12 Measuring faimess' Precise mathematical definitions of timess
  13. 13 Measurement is everywhere
  14. 14 Measurement modeling and NLP
  15. 15 Measuring "bias" in NLP systems
  16. 16 Potential constructs of interest: Representational harms from NLP systems
  17. 17 Example 1: Word embeddings

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.