arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.03390cs.CYcs.AIcs.CLcs.LG
收藏

词嵌入中的性别偏见:频率、句法和语义的综合分析

Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics

University of Washington(华盛顿大学);Information School(信息学院);Birla Institute of Technology and Science(比尔拉科学技术学院);Harvard University(哈佛大学)

Aylin Caliskan, Pimparkar Parth Ajay, Tessa Charlesworth, Robert Wolfe, Mahzarin R. Banaji

摘要:

语言语料库中的统计数据将众所周知的社会偏见编码到词嵌入中。在这里,我们专注于性别,以全面分析在互联网语料库上训练的广泛使用的静态英语词嵌入中基于群体的偏见(GloVe 2014,fastText 2017)。使用单类别词嵌入关联测试,我们证明了性别偏见的普遍存在,也显示出差异:(1)与男性和女性相关的词的频率;(b)性别相关词的词性标签;(c)性别相关词的语义类别;(d)性别相关词的效价,唤醒和优势。首先,在词频方面:我们发现,在词汇表中最常见的1,000个单词中,77%与男性的联系比女性更多,这为英语世界的日常语言中男性默认提供了直接证据。第二,转向词性:与男性相关的词最多的通常是动词(例如,fight,overpower),而与女性相关的最多的词通常是形容词和副词(例如,情感上的,情感上的)。嵌入中的性别偏见也渗透到词性中。第三,对于语义类别:自下而上,对与每个性别相关的前1,000个词进行聚类分析。与男性相关的概念包括大型科技、工程、宗教、体育和暴力的角色和领域;相比之下,与女性相关的概念则不太关注角色,包括女性特有的诽谤和性内容,以及外观和厨房术语。第四,从一个约20,000字的词汇,使用人类的评级的字的效价,唤醒,和优势,我们发现,男性相关的词更高的唤醒和优势,而女性相关的词更高的效价。

英文摘要:

The statistical regularities in language corpora encode well-known social biases into word embeddings. Here, we focus on gender to provide a comprehensive analysis of group-based biases in widely-used static English word embeddings trained on internet corpora (GloVe 2014, fastText 2017). Using the Single-Category Word Embedding Association Test, we demonstrate the widespread prevalence of gender biases that also show differences in: (1) frequencies of words associated with men versus women; (b) part-of-speech tags in gender-associated words; (c) semantic categories in gender-associated words; and (d) valence, arousal, and dominance in gender-associated words. First, in terms of word frequency: we find that, of the 1,000 most frequent words in the vocabulary, 77% are more associated with men than women, providing direct evidence of a masculine default in the everyday language of the English-speaking world. Second, turning to parts-of-speech: the top male-associated words are typically verbs (e.g., fight, overpower) while the top female-associated words are typically adjectives and adverbs (e.g., giving, emotionally). Gender biases in embeddings also permeate parts-of-speech. Third, for semantic categories: bottom-up, cluster analyses of the top 1,000 words associated with each gender. The top male-associated concepts include roles and domains of big tech, engineering, religion, sports, and violence; in contrast, the top female-associated concepts are less focused on roles, including, instead, female-specific slurs and sexual content, as well as appearance and kitchen terms. Fourth, using human ratings of word valence, arousal, and dominance from a ~20,000 word lexicon, we find that male-associated words are higher on arousal and dominance, while female-associated words are higher on valence.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑