Word Embeddings (Also) Encode Human Personality Stereotypes
Word Embeddings (Also) Encode Human Personality Stereotypes
复制标题
词嵌入（还）编码人类性格刻板印象
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
A. Nenkova
中科院分区：
文献类型：
--
作者：
Oshin Agarwal;Funda Durupinar;N. Badler;A. Nenkova
在文本上训练的单词表征再现了与性别、种族和年龄相关的人类内隐偏见。已经开发了消除这种偏差的方法。在这里，我们提出的结果表明，人类的刻板印象存在，即使是更微妙的判断，如个性，为各种身份的人超出了通常的法律保护的属性，这些都是类似的文字表征。具体来说，我们收集了人类对一个人的大五人格特质的判断，这些判断完全来自于职业、国籍或对一个假设的人的普通名词描述。对数据的分析表明，人们中存在大量具有统计意义的定型观念。然后，我们证明了在词汇表征中捕获的偏见与记录的人类偏见在统计上显着相关。我们的研究结果，显示偏见的一大套人的描述符，这种细微差别的特点提出了怀疑的可行性，广泛和公平地应用去偏见的方法，并要求开发新的方法，审计语言技术系统和资源。
Word representations trained on text reproduce human implicit bias related to gender, race and age. Methods have been developed to remove such bias. Here, we present results that show that human stereotypes exist even for much more nuanced judgments such as personality, for a variety of person identities beyond the typically legally protected attributes and that these are similarly captured in word representations. Specifically, we collected human judgments about a person’s Big Five personality traits formed solely from information about the occupation, nationality or a common noun description of a hypothetical person. Analysis of the data reveals a large number of statistically significant stereotypes in people. We then demonstrate the bias captured in lexical representations is statistically significantly correlated with the documented human bias. Our results, showing bias for a large set of person descriptors for such nuanced traits put in doubt the feasibility of broadly and fairly applying debiasing methods and call for the development of new methods for auditing language technology systems and resources.
影响因子：
7.6
作者：
Greenwald, AG;McGhee, DE;Schwartz, JLK
通讯作者：
Schwartz, JLK
DOI：
10.18653/v1/n18-2003
发表时间：
2018-04
期刊：
ArXiv
影响因子：
--
作者：
Jieyu Zhao;Tianlu Wang;Mark Yatskar;Vicente Ordonez;Kai-Wei Chang
通讯作者：
Jieyu Zhao;Tianlu Wang;Mark Yatskar;Vicente Ordonez;Kai-Wei Chang