Gender bias in transformers: A comprehensive review of detection and mitigation strategies

被引:5
作者
Nemani, Praneeth [1 ,4 ]
Joel, Yericherla Deepak [2 ]
Vijay, Palla [2 ]
Liza, Farhana Ferdouzi [3 ]
机构
[1] Department of Computer Science and Engineering, IIIT Naya Raipur, Chhattisgarh, India
[2] Department of Data Science and Artificial Intelligence, IIIT Naya Raipur, Chhattisgarh, India
[3] School of Computing Sciences, University of East Anglia (UEA), Norwich, United Kingdom
[4] College of Engineering and Applied Science, University of Colorado Boulder, CO, United States
来源
Natural Language Processing Journal | 2024年 / 6卷
关键词
Computational linguistics;
D O I
10.1016/j.nlp.2023.100047
中图分类号
学科分类号
摘要
Gender bias in artificial intelligence (AI) has emerged as a pressing concern with profound implications for individuals’ lives. This paper presents a comprehensive survey that explores gender bias in Transformer models from a linguistic perspective. While the existence of gender bias in language models has been acknowledged in previous studies, there remains a lack of consensus on how to measure and evaluate this bias effectively. Our survey critically examines the existing literature on gender bias in Transformers, shedding light on the diverse methodologies and metrics employed to assess bias. Several limitations in current approaches to measuring gender bias in Transformers are identified, encompassing the utilization of incomplete or flawed metrics, inadequate dataset sizes, and a dearth of standardization in evaluation methods. Furthermore, our survey delves into the potential ramifications of gender bias in Transformers for downstream applications, including dialogue systems and machine translation. We underscore the importance of fostering equity and fairness in these systems by emphasizing the need for heightened awareness and accountability in developing and deploying language technologies. This paper serves as a comprehensive overview of gender bias in Transformer models, providing novel insights and offering valuable directions for future research in this critical domain. © 2023 The Author(s)
引用
收藏
相关论文
empty
未找到相关数据