Gender Bias in Coreference Resolution
2018-04-25NAACL 2018Code Available1· sign in to hype
Rachel Rudinger, Jason Naradowsky, Brian Leonard, Benjamin Van Durme
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/rudinger/winogender-schemasOfficialIn papernone★ 0
- github.com/anthropics/evalsnone★ 338
- github.com/mapmeld/disambiguation_qnone★ 0
- github.com/uclanlp/socialbias-dataset-construction-biasesnone★ 0
Abstract
We present an empirical study of gender bias in coreference resolution systems. We first introduce a novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender. With these "Winogender schemas," we evaluate and confirm systematic gender bias in three publicly-available coreference resolution systems, and correlate this bias with real-world and textual gender statistics.