Understanding Gender Bias in Knowledge Base Embeddings

Yupei Du; Qi Zheng; Yuanbin Wu; Man Lan; Yan Yang; Meirong Ma

ACL 2022long10 citations

Understanding Gender Bias in Knowledge Base Embeddings

Yupei Du, Qi Zheng, Yuanbin Wu, Man Lan, Yan Yang, Meirong Ma

Abstract

Knowledge base (KB) embeddings have been shown to contain gender biases. In this paper, we study two questions regarding these biases: how to quantify them, and how to trace their origins in KB? Specifically, first, we develop two novel bias measures respectively for a group of person entities and an individual person entity. Evidence of their validity is observed by comparison with real-world census data. Second, we use the influence function to inspect the contribution of each triple in KB to the overall group bias. To exemplify the potential applications of our study, we also present two strategies (by adding and removing KB triples) to mitigate gender biases in KB embeddings.

BibTeX

@inproceedings{du-etal-2022-understanding,
    title = "Understanding Gender Bias in Knowledge Base Embeddings",
    author = "Du, Yupei  and
      Zheng, Qi  and
      Wu, Yuanbin  and
      Lan, Man  and
      Yang, Yan  and
      Ma, Meirong",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.98/",
    doi = "10.18653/v1/2022.acl-long.98",
    pages = "1381--1395"
}