Understanding Gender Bias in Knowledge Base Embeddings

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

doi:10.18653/v1/2022.acl-long.98

Understanding Gender Bias in Knowledge Base Embeddings

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

^*Corresponding author for this work

School of Computer Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Scopus citations

Abstract

Knowledge base (KB) embeddings have been shown to contain gender biases (Fisher et al., 2020b). 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 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.

Original language	English
Title of host publication	ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Editors	Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Publisher	Association for Computational Linguistics (ACL)
Pages	1381-1395
Number of pages	15
ISBN (Electronic)	9781955917216
DOIs	https://doi.org/10.18653/v1/2022.acl-long.98
State	Published - 2022
Event	60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 - Dublin, Ireland Duration: 22 May 2022 → 27 May 2022

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
Volume	1
ISSN (Print)	0736-587X

Conference

Conference	60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
Country/Territory	Ireland
City	Dublin
Period	22/05/22 → 27/05/22

Access to Document

10.18653/v1/2022.acl-long.98

Cite this

Du, Y., Zheng, Q., Wu, Y., Lan, M., Yang, Y., & Ma, M. (2022). Understanding Gender Bias in Knowledge Base Embeddings. In S. Muresan, P. Nakov, & A. Villavicencio (Eds.), ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (pp. 1381-1395). (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 1). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.acl-long.98

Du, Yupei ; Zheng, Qi ; Wu, Yuanbin et al. / Understanding Gender Bias in Knowledge Base Embeddings. ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). editor / Smaranda Muresan ; Preslav Nakov ; Aline Villavicencio. Association for Computational Linguistics (ACL), 2022. pp. 1381-1395 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{a780b0a5b7704b8e8adcca287b19ffee,

title = "Understanding Gender Bias in Knowledge Base Embeddings",

abstract = "Knowledge base (KB) embeddings have been shown to contain gender biases (Fisher et al., 2020b). 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 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.",

author = "Yupei Du and Qi Zheng and Yuanbin Wu and Man Lan and Yan Yang and Meirong Ma",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 ; Conference date: 22-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.18653/v1/2022.acl-long.98",

language = "英语",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

pages = "1381--1395",

editor = "Smaranda Muresan and Preslav Nakov and Aline Villavicencio",

booktitle = "ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

address = "澳大利亚",

}

Du, Y, Zheng, Q, Wu, Y, Lan, M, Yang, Y & Ma, M 2022, Understanding Gender Bias in Knowledge Base Embeddings. in S Muresan, P Nakov & A Villavicencio (eds), ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Proceedings of the Annual Meeting of the Association for Computational Linguistics, vol. 1, Association for Computational Linguistics (ACL), pp. 1381-1395, 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022, Dublin, Ireland, 22/05/22. https://doi.org/10.18653/v1/2022.acl-long.98

Understanding Gender Bias in Knowledge Base Embeddings. / Du, Yupei; Zheng, Qi; Wu, Yuanbin et al.
ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). ed. / Smaranda Muresan; Preslav Nakov; Aline Villavicencio. Association for Computational Linguistics (ACL), 2022. p. 1381-1395 (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Understanding Gender Bias in Knowledge Base Embeddings

AU - Du, Yupei

AU - Zheng, Qi

AU - Wu, Yuanbin

AU - Lan, Man

AU - Yang, Yan

AU - Ma, Meirong

PY - 2022

Y1 - 2022

N2 - Knowledge base (KB) embeddings have been shown to contain gender biases (Fisher et al., 2020b). 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 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.

AB - Knowledge base (KB) embeddings have been shown to contain gender biases (Fisher et al., 2020b). 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 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.

UR - https://www.scopus.com/pages/publications/85139896791

U2 - 10.18653/v1/2022.acl-long.98

DO - 10.18653/v1/2022.acl-long.98

M3 - 会议稿件

AN - SCOPUS:85139896791

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 1381

EP - 1395

BT - ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

A2 - Muresan, Smaranda

A2 - Nakov, Preslav

A2 - Villavicencio, Aline

PB - Association for Computational Linguistics (ACL)

T2 - 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022

Y2 - 22 May 2022 through 27 May 2022

ER -

Du Y, Zheng Q, Wu Y, Lan M, Yang Y, Ma M. Understanding Gender Bias in Knowledge Base Embeddings. In Muresan S, Nakov P, Villavicencio A, editors, ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL). 2022. p. 1381-1395. (Proceedings of the Annual Meeting of the Association for Computational Linguistics). doi: 10.18653/v1/2022.acl-long.98

Understanding Gender Bias in Knowledge Base Embeddings

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this