Papers
arxiv:1804.09301

Gender Bias in Coreference Resolution

Published on Apr 25, 2018
Authors:
,
,
,

Abstract

A study reveals and analyzes gender bias in coreference resolution systems using a novel set of gender-neutral minimal pair sentences.

AI-generated summary

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.

Community

maybe for @thomwolf ?

Sign up or log in to comment

Models citing this paper 297

Browse 297 models citing this paper

Datasets citing this paper 1

Spaces citing this paper 1,532

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.