arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.06898cs.CLcs.LG
收藏

减轻机器学习数据集中的性别偏见

Mitigating Gender Bias in Machine Learning Data Sets

University College Dublin(都柏林大学学院)

Susan Leavy, Gerardine Meaney, Karen Wade, Derek Greene

摘要:

人工智能有能力放大和延续社会偏见,并为社会带来深刻的伦理影响。在招聘广告和招聘工具的背景下,由于依赖于潜在的语言处理和推荐算法,性别偏见已被确定。解决这些问题的尝试涉及测试学习关联,将公平性概念集成到机器学习中,并对训练数据进行更严格的分析。考虑到性别意识形态嵌入语言的复杂方式,在文本数据上训练算法时减轻偏见尤其具有挑战性。本文提出了一个识别机器学习训练数据中性别偏见的框架,利用性别理论和社会语言学,系统地指出文本训练数据和相关神经词嵌入模型中的偏见水平,从而突出了从训练数据中消除偏见并严格评估其影响的途径。

英文摘要:

Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due to their reliance on underlying language processing and recommendation algorithms. Attempts to address such issues have involved testing learned associations, integrating concepts of fairness to machine learning and performing more rigorous analysis of training data. Mitigating bias when algorithms are trained on textual data is particularly challenging given the complex way gender ideology is embedded in language. This paper proposes a framework for the identification of gender bias in training data for machine learning.The work draws upon gender theory and sociolinguistics to systematically indicate levels of bias in textual training data and associated neural word embedding models, thus highlighting pathways for both removing bias from training data and critically assessing its impact.

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。

↑