Recent work has shown pre-trained language models capture social biases from
the large amounts of text they are trained on. This has attracted attention to
developing techniques that mitigate such biases. In this work, we perform an
empirical survey of five recently proposed bias mitigation techniques:
Counterfactual Data Augmentation (CDA), Dropout, Iterative Nullspace
Projection, Self-Debias, and SentenceDebias. We quantify the effectiveness of
each technique using three intrinsic bias benchmarks while also measuring the
impact of these techniques on a model's language modeling ability, as well as
its performance on downstream NLU tasks. We experimentally find that: (1)
Self-Debias is the strongest debiasing technique, obtaining improved scores on
all bias benchmarks; (2) Current debiasing techniques perform less consistently
when mitigating non-gender biases; And (3) improvements on bias benchmarks such
as StereoSet and CrowS-Pairs by using debiasing strategies are often
accompanied by a decrease in language modeling ability, making it difficult to
determine whether the bias mitigation was effective.

本文调查了五种最近提出的消除算法：CDA、Dropout、Iterative Nullspace Projection、Self-Debias 和 SentenceDebias 的有效性。实验结果显示，Self-Debias 是最有效的去偏置技术。但是现有去偏置技术在减轻非性别偏差方面表现不一致，同时算法会降低模型的语言建模能力，难以确定去偏置的效果。