arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.03353cs.CLcs.AIcs.CY
收藏

“事实”的生命周期:知识图谱中社会偏见综述

The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphs

Universität Hamburg(汉堡大学);Hamburger Informatik Technologie-Center e.V. (HITeC)(汉堡信息技术中心协会)

Angelie Kraft, Ricardo Usbeck

AI总结:

本文综述了知识图谱生命周期各阶段中社会偏见的来源、传播与呈现方式,分析现有测量和缓解方法的局限,并提出未来研究方向。

摘要:

知识图谱正越来越多地用于大量下游任务,或用于增强统计模型以提高事实性。然而,社会偏见被铭刻在这些表示中,并向下游传播。我们对涉及知识图谱生命周期不同步骤偏见的文献进行了批判性分析。我们调查了引入偏见的因素,以及随后由知识图谱及其嵌入版本所呈现的偏见。我们讨论了现有测量和缓解策略的局限性,并提出了前进路径。

英文摘要:

Knowledge graphs are increasingly used in a plethora of downstream tasks or in the augmentation of statistical models to improve factuality. However, social biases are engraved in these representations and propagate downstream. We conducted a critical analysis of literature concerning biases at different steps of a knowledge graph lifecycle. We investigated factors introducing bias, as well as the biases that are rendered by knowledge graphs and their embedded versions afterward. Limitations of existing measurement and mitigation strategies are discussed and paths forward are proposed.

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。

↑