Gender Bias in Contextualized Word Embeddings

In this paper, we quantify, analyze and mitigate gender bias exhibited in ELMo’s contextualized word vectors. First, we conduct several intrinsic analyses and find that (1) training data for ELMo contains significantly more male than female entities, (2) the trained ELMo embeddings systematically encode gender information and (3) ELMo unequally encodes gender information about male and female entities. Then, we show that a state-of-the-art coreference system that depends on ELMo inherits its bias and demonstrates significant bias on the WinoBias probing corpus. Finally, we explore two methods to mitigate such gender bias and show that the bias demonstrated on WinoBias can be eliminated.

在本文中，我们首先量化，分析和减轻Elmo的性别偏见。嵌入系统地编码性别信息，（3）Elmo不平等地编码有关男性和女性实体的性别信息。取决于Elmo的核心系统继承了其偏差，并在Winobias探测语料库上证明了显着的偏见。