BriefGPT.xyz
May, 2020
通过后验正则化减轻分布中的性别偏见放大
Mitigating Gender Bias Amplification in Distribution by Posterior Regularization
HTML
PDF
Shengyu Jia, Tao Meng, Jieyu Zhao, Kai-Wei Chang
TL;DR
研究表明,基于先进的机器学习技术的自然语言处理中存在性别偏见放大问题,本文提出了基于后验正则化的偏见缓解方法,旨在降低性别偏见的放大,实验证明该方法可在保证少量性能损失的情况下,几乎完全消除了分布中的偏见放大。
Abstract
Advanced
machine learning
techniques have boosted the performance of
natural language processing
. Nevertheless, recent studies, e.g., Zhao et al. (2017) show that these techniques inadvertently capture the
→