Antonis Maronikolakis, Philip Baader, Hinrich Schütze
TL;DR为了解决仇恨言论不断增长的问题，本文探索了种族、性别交叉轴线上仇恨言论数据集的分析，发现 African American English、男性和 AAE+男性推文中存在强烈的偏见，BERT 模型会传播这种偏见，但通过平衡训练数据可以实现更公平的性别模型。
Abstract
To tackle the rising phenomenon of hate speech, efforts have been made towards data curation and analysis. When it comes to analysis of bias, previous work has focused predominantly on race. In our work, we furth