arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.00126cs.SIcs.CYcs.LG
收藏

有毒语音检测中的偏差处理研究综述

Handling Bias in Toxic Speech Detection: A Survey

IIIT Delhi(德里印度理工学院信息技术学院);IIT Delhi(德里印度理工学院)

Tanmay Garg, Sarah Masud, Tharun Suresh, Tanmoy Chakraborty

摘要:

由于其固有的主观性,检测在线毒性一直是一个挑战。背景、地理、社会政治气候以及帖子生产者和消费者的背景等因素在确定内容是否可以被标记为有毒内容方面发挥着至关重要的作用。因此,在生产中采用自动化毒性检测模型可能会导致他们首先要帮助的各种群体被边缘化。它激发了研究人员对检查无意偏见及其缓解的兴趣。由于作品的新生和多面性,完整的文学在术语、技术和发现上都是混乱的。在本文中,我们把一个系统的研究的局限性和挑战,现有的方法,以减轻偏见,在毒性检测。我们密切关注建议的方法,用于评估和减轻有毒语音检测的偏见。为了研究现有方法的局限性,我们还进行了一个案例研究,介绍了偏见转移的概念,由于基于知识的偏见缓解。调查最后概述了关键挑战,研究差距和未来方向。虽然减少在线平台上的毒性仍然是一个活跃的研究领域,但对各种偏见及其缓解策略的系统研究将有助于研究界产生强大而公平的模型。

英文摘要:

Detecting online toxicity has always been a challenge due to its inherent subjectivity. Factors such as the context, geography, socio-political climate, and background of the producers and consumers of the posts play a crucial role in determining if the content can be flagged as toxic. Adoption of automated toxicity detection models in production can thus lead to a sidelining of the various groups they aim to help in the first place. It has piqued researchers' interest in examining unintended biases and their mitigation. Due to the nascent and multi-faceted nature of the work, complete literature is chaotic in its terminologies, techniques, and findings. In this paper, we put together a systematic study of the limitations and challenges of existing methods for mitigating bias in toxicity detection. We look closely at proposed methods for evaluating and mitigating bias in toxic speech detection. To examine the limitations of existing methods, we also conduct a case study to introduce the concept of bias shift due to knowledge-based bias mitigation. The survey concludes with an overview of the critical challenges, research gaps, and future directions. While reducing toxicity on online platforms continues to be an active area of research, a systematic study of various biases and their mitigation strategies will help the research community produce robust and fair models.

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。

↑