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.
Get this paper in your agent:
hf papers read 1804.09301 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 309
Browse 309 models citing this paperDatasets citing this paper 1
Spaces citing this paper 3,042
Browse 3,042 spaces citing this paperCollections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.