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