论文标题
关于自然语言处理中偏见和公平性的调查
A Survey on Bias and Fairness in Natural Language Processing
论文作者
论文摘要
随着NLP模型与人们的日常生活变得更加融合，重要的是要检查这些系统的使用的社会效果。尽管这些模型了解语言并提高了在下游任务上的准确性，但有证据表明，这些模型会扩大性别，种族和文化刻板印象，并在许多情况下导致恶性循环。在这项调查中，我们分析了偏见的起源，公平的定义以及NLP的不同子场如何减轻偏见。我们终于讨论了未来的研究如何努力消除NLP算法的有害偏见。
As NLP models become more integrated with the everyday lives of people, it becomes important to examine the social effect that the usage of these systems has. While these models understand language and have increased accuracy on difficult downstream tasks, there is evidence that these models amplify gender, racial and cultural stereotypes and lead to a vicious cycle in many settings. In this survey, we analyze the origins of biases, the definitions of fairness, and how different subfields of NLP mitigate bias. We finally discuss how future studies can work towards eradicating pernicious biases from NLP algorithms.
