GEST

Dataset

GEST – a manually created dataset designed to measure gender-stereotypical reasoning in language models and machine translation systems. GEST contains samples for 16 gender stereotypes about men and women (e.g., Women are beautiful, Men are leaders) that are compatible with the English language and 9 Slavic languages. The definition of said stereotypes was informed by gender experts.

Hugging Face GitHub Paper

Contributors: NLP KInIT
WUDAP KInIT
Ethics KInIT
License: Apache 2.0
Language: eng, sk, by, hrv, cz, pl, rus, srb, si, ua
Modality: Text
Domain: General
Task: Gender stereotypical reasoning and translation