Re:Show HN: Word2Bits – Quantized Word Vectors
by fvdessen on Tuesday March 20, 2018 @12:32PM
(#16630101)
That's because what's called 'debiasing' is not actually removing bias but adding another opposite one at the superficial layers we can actually notice.
[ Parent
| on HN ]
Re:Show HN: Word2Bits – Quantized Word Vectors
by rspeer on Tuesday March 20, 2018 @12:59PM
(#16630386)
That's possibly a fair description of the kind of as-late-as-possible de-biasing that I find insufficient.
I think there is not nearly enough research into de-biasing at training time, perhaps because it would be discouraged by the reward structure of our field.
("You mean I can make my model more complex and my paper longer, and in return I lose the 0.15% accuracy gain that's the entire reason I could call the result 'state of the art'? Sure, I'll get right on that!")