Toward Gender-Inclusive Coreference Resolution

Yang Trista Cao, Hal Daumé III


Abstract
Correctly resolving textual mentions of people fundamentally entails making inferences about those people. Such inferences raise the risk of systemic biases in coreference resolution systems, including biases that can harm binary and non-binary trans and cis stakeholders. To better understand such biases, we foreground nuanced conceptualizations of gender from sociology and sociolinguistics, and develop two new datasets for interrogating bias in crowd annotations and in existing coreference resolution systems. Through these studies, conducted on English text, we confirm that without acknowledging and building systems that recognize the complexity of gender, we build systems that lead to many potential harms.
Anthology ID:
2020.acl-main.418
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4568–4595
Language:
URL:
https://aclanthology.org/2020.acl-main.418
DOI:
10.18653/v1/2020.acl-main.418
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.418.pdf
Video:
 http://slideslive.com/38929030
Code
 TristaCao/into_inclusivecoref
Data
GICorefMAPGAP Coreference DatasetaGender