论文标题
缓解机器学习数据集中的性别偏见
Mitigating Gender Bias in Machine Learning Data Sets
论文作者
论文摘要
人工智能有能力扩大和永久化社会偏见，并对社会产生深远的道德意义。性别偏见已在就业广告和招聘工具的背景下确定，因为它们依赖基本语言处理和建议算法。解决此类问题的尝试涉及测试学习的关联，将公平性的概念整合到机器学习中，并对培训数据进行更严格的分析。鉴于性别意识形态在语言中嵌入了复杂的方式，对算法进行训练时，缓解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。该工作借鉴了性别理论和社会语言学，以系统地表明文本培训数据中的偏见和相关的神经单词嵌入模型，从而突出了从训练数据中删除偏见的途径，并批判性地评估了其影响。
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.
