国产bbaaaaa片,成年美女黄网站色视频免费,成年黄大片,а天堂中文最新一区二区三区,成人精品视频一区二区三区尤物

首頁> 外文會(huì)議>Workshop on gender bias in natural language processing;Annual meeting of the Association for Computational Linguistics >Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories
【24h】

Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories

機(jī)譯：測(cè)量跨域詞嵌入中的性別偏見并發(fā)現(xiàn)新的性別偏見詞類別

獲取原文
  • 摘要
  • 著錄項(xiàng)
  • 相似文獻(xiàn)
  • 相關(guān)主題

摘要

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.
機(jī)譯：先前的工作表明，詞嵌入可以捕捉人類的刻板印象，包括性別偏見。但是，缺乏研究來檢驗(yàn)跨不同領(lǐng)域的詞嵌入中特定性別偏見類別的存在。本文旨在通過將WEAT偏向檢測(cè)方法應(yīng)用于從四個(gè)不同領(lǐng)域進(jìn)行語料庫訓(xùn)練的四組詞嵌入來填補(bǔ)這一空白：新聞，社交網(wǎng)絡(luò)，生物醫(yī)學(xué)和從維基百科（GAP）提取的性別平衡語料庫。我們發(fā)現(xiàn)某些領(lǐng)域肯定比其他領(lǐng)域更容易出現(xiàn)性別偏見，并且存在的性別偏見的類別對(duì)于每組詞嵌入也有所不同。我們發(fā)現(xiàn)GAP中存在一些性別偏見。我們還提出了一種簡(jiǎn)單但新穎的方法，用于通過聚類詞嵌入來發(fā)現(xiàn)新的偏好類別。我們通過WEAT的假設(shè)檢驗(yàn)機(jī)制驗(yàn)證了此方法，發(fā)現(xiàn)它對(duì)于擴(kuò)展文獻(xiàn)中通常使用的相對(duì)較少的一組知名的性別偏見詞類別很有用。

著錄項(xiàng)

相似文獻(xiàn)

  • 外文文獻(xiàn)
  • 中文文獻(xiàn)
  • 專利
獲取原文

客服郵箱：kefu@zhangqiaokeyan.com

京公網(wǎng)安備：11010802029741號(hào) ICP備案號(hào)：京ICP備15016152號(hào)-6 六維聯(lián)合信息科技 (北京) 有限公司?版權(quán)所有

  • 客服微信

  • 服務(wù)號(hào)