OSCaR：正交子空间校正和词嵌入中的偏差校正
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings
摘要：
众所周知，语言表征带有刻板偏见，因此，导致下游任务中有偏见的预测。虽然现有的方法在通过线性投影减轻偏差方面是有效的，但是这样的方法过于激进：它们不仅去除偏差，而且从词嵌入中擦除有价值的信息。我们开发了新的措施来评估特定的信息保留，证明偏见消除和信息保留之间的权衡。为了解决这一挑战，我们提出了OSCaR（正交子空间校正和整流），一种偏差缓解方法，专注于解开概念之间的偏见的关联，而不是删除概念批发。我们对性别偏见的实验表明，OSCaR是一种平衡良好的方法，可以确保语义信息保留在嵌入中，偏见也被有效地减轻。
英文摘要：
Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks. While existing methods are effective at mitigating biases by linear projection, such methods are too aggressive: they not only remove bias, but also erase valuable information from word embeddings. We develop new measures for evaluating specific information retention that demonstrate the tradeoff between bias removal and information retention. To address this challenge, we propose OSCaR (Orthogonal Subspace Correction and Rectification), a bias-mitigating method that focuses on disentangling biased associations between concepts instead of removing concepts wholesale. Our experiments on gender biases show that OSCaR is a well-balanced approach that ensures that semantic information is retained in the embeddings and bias is also effectively mitigated.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
