Google Developers Blog company blog
Text Embedding Models Contain Bias
As Machine Learning practitioners, when faced with a task, we usually select or train a model primarily based on how well it performs on that task. For example, say we're building a system to classify whether a movie review is positive or negative. We take 5 different models and see how well each performs this task:
- Points
- 222
- HN comments
- 202
- Submissions
- 1
- Cited by
- 3 commenters
AI & Machine LearningSociety, Policy & Culture2018
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Apr 17, 2018 | Text Embedding Models Contain Bias by gajju3588 | 222 | 202 |
Cited in comments
Linked from 3 Hacker News comments by 3 different people, from May 2018 to Oct 2019.
Most recent:
- repolfx · Oct 17, 2019
- samfriedman · May 25, 2018
- dmazin · May 8, 2018
