Interdependencies of Gender and Race in Contextualized Word Embeddings
Interdependencies of Gender and Race in Contextualized Word Embeddings
复制标题
语境化词嵌入中性别和种族的相互依赖性
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
C. Fellbaum
中科院分区：
文献类型：
--
作者：
May Jiang;C. Fellbaum
近年来，人们对性别嵌入中的偏见以及在较小程度上的种族研究激增。但是，这些研究中很少有人注意种族和性别的关键交集。在此案例研究中，我们分析了给定名称的上下文化词嵌入性别和种族的维度，从BERT拿走，并研究其相互作用的性质和细微差别。我们发现，这些人口统计轴通常在身体和概念上分开，但实际上是相互依存的，因此不可理解。此外，我们表明，基于语言中默认设置的人口统计学维度（例如代词中）可能会冒着呈现具有多个边缘化身份的组的群体。我们通过讨论交叉性对未来对NLP中偏见和偏见的研究的重要性和含义来结束。
Recent years have seen a surge in research on the biases in word embeddings with respect to gender and, to a lesser extent, race. Few of these studies, however, have given attention to the critical intersection of race and gender. In this case study, we analyze the dimensions of gender and race in contextualized word embeddings of given names, taken from BERT, and investigate the nature and nuance of their interaction. We find that these demographic axes, though typically treated as physically and conceptually separate, are in fact interdependent and thus inadvisable to consider in isolation. Further, we show that demographic dimensions predicated on default settings in language, such as in pronouns, may risk rendering groups with multiple marginalized identities invisible. We conclude by discussing the importance and implications of intersectionality for future studies on bias and debiasing in NLP.
影响因子：
7.6
作者：
Greenwald, AG;McGhee, DE;Schwartz, JLK
通讯作者：
Schwartz, JLK
黑人之于罪犯就像白人之于警察：检测和消除词嵌入中的多类偏差
DOI：
--
发表时间：
2019
期刊：
2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL
影响因子：
--
作者：
Manzini, Thomas;Lim, Yao Chong;Tsvetkov, Yulia;Black, Alan W
通讯作者：
Black, Alan W