De-biasing language
O'Reilly Media - Ideas
APRIL 2, 2019
The toughest bias problems are often the ones you only think you’ve solved. In a recent paper, Hila Gonen and Yoav Goldberg argue that methods for de-biasing language models aren’t effective ; they make bias less apparent, but don’t actually remove it. De-biasing might even make bias more dangerous by hiding it, rather than leaving it out in the open.
Let's personalize your content