Papers with biased models of language processing
Diverse Adversaries for Mitigating Bias in Training (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing adversarial methods only partially mitigate the problem of model bias, added to which their training procedures are unstable. |
| Approach: | They propose a method where discriminators are encouraged to learn orthogonal hidden representations from one another to reduce model bias. |
| Outcome: | The proposed method significantly reduces bias and stability of training over standard methods. |