Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories
Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories
复制标题
DOI：
10.18653/v1/w19-3804
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
K. Chaloner;Alfredo Maldonado
中科院分区：
文献类型：
--
作者：
K. Chaloner;Alfredo Maldonado
先前的研究表明，单词嵌入捕捉到了人类的刻板印象，包括性别偏见。然而，在不同领域的词汇嵌入中，缺乏测试特定性别偏见类别存在的研究。为了填补这一空白，本文将Weat偏见检测方法应用于四个不同领域的语料库上的四组词嵌入训练：新闻、社交网络、生物医学和从维基百科提取的性别平衡语料库(GAP)。我们发现，某些领域肯定比其他领域更容易出现性别偏见，而且性别偏见的类别也因每组词的嵌入而异。我们发现GAP中存在一些性别偏见。我们还提出了一种简单而新颖的方法，通过聚类词嵌入来发现新的倾向性类别。我们通过Weat的假设检验机制对该方法进行了验证，发现它对于扩展文献中常用的相对较小的性别偏见词类非常有用。
Prior work has shown that word embeddings capture human stereotypes, including gender bias. However, there is a lack of studies testing the presence of specific gender bias categories in word embeddings across diverse domains. This paper aims to fill this gap by applying the WEAT bias detection method to four sets of word embeddings trained on corpora from four different domains: news, social networking, biomedical and a gender-balanced corpus extracted from Wikipedia (GAP). We find that some domains are definitely more prone to gender bias than others, and that the categories of gender bias present also vary for each set of word embeddings. We detect some gender bias in GAP. We also propose a simple but novel method for discovering new bias categories by clustering word embeddings. We validate this method through WEAT’s hypothesis testing mechanism and find it useful for expanding the relatively small set of well-known gender bias word categories commonly used in the literature.