no code implementations • ACL 2022 • Aurélie Névéol, Yoann Dupont, Julien Bezançon, Karën Fort
We build on the US-centered CrowS-pairs dataset to create a multilingual stereotypes dataset that allows for comparability across languages while also characterizing biases that are specific to each country and language.
no code implementations • JEP/TALN/RECITAL 2022 • Aurélie Névéol, Yoann Dupont, Julien Bezançon, Karën Fort
Nous montrons que quatre modèles de langue favorisent les énoncés qui expriment des stéréotypes dans la plupart des catégories.
no code implementations • NIDCP (LREC) 2022 • Karën Fort, Aurélie Névéol, Yoann Dupont, Julien Bezançon
We created three tasks on the LanguageARC citizen science platform to assist with the translation of an existing resource from English into French as well as the collection of complementary resources in native French.