BriefGPT.xyz
Mar, 2022
自然语言处理中偏差和公平性调查
A Survey on Bias and Fairness in Natural Language Processing
HTML
PDF
Rajas Bansal
TL;DR
本次调查分析了NLP模型的社会影响，探讨了NLP算法中存在性别、种族和文化偏见的根源，定义了公平性，并说明了NLP各个子领域如何减少系统存在的偏见，最终讨论了未来研究如何消除NLP算法中的有害偏见。
Abstract
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 incre
→