@inproceedings{neveol-etal-2022-french,
title = "{F}rench {C}row{S}-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than {E}nglish",
author = {N{\'e}v{\'e}ol, Aur{\'e}lie and
Dupont, Yoann and
Bezan{\c{c}}on, Julien and
Fort, Kar{\"e}n},
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.583/",
doi = "10.18653/v1/2022.acl-long.583",
pages = "8521--8531",
abstract = "Warning: This paper contains explicit statements of offensive stereotypes which may be upsetting. Much work on biases in natural language processing has addressed biases linked to the social and cultural experience of English speaking individuals in the United States. We seek to widen the scope of bias studies by creating material to measure social bias in language models (LMs) against specific demographic groups in France. 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. We introduce 1,679 sentence pairs in French that cover stereotypes in ten types of bias like gender and age. 1,467 sentence pairs are translated from CrowS-pairs and 212 are newly crowdsourced. The sentence pairs contrast stereotypes concerning underadvantaged groups with the same sentence concerning advantaged groups. We find that four widely used language models (three French, one multilingual) favor sentences that express stereotypes in most bias categories. We report on the translation process from English into French, which led to a characterization of stereotypes in CrowS-pairs including the identification of US-centric cultural traits. We offer guidelines to further extend the dataset to other languages and cultural environments."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="neveol-etal-2022-french">
<titleInfo>
<title>French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoann</namePart>
<namePart type="family">Dupont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Bezançon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karën</namePart>
<namePart type="family">Fort</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Warning: This paper contains explicit statements of offensive stereotypes which may be upsetting. Much work on biases in natural language processing has addressed biases linked to the social and cultural experience of English speaking individuals in the United States. We seek to widen the scope of bias studies by creating material to measure social bias in language models (LMs) against specific demographic groups in France. 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. We introduce 1,679 sentence pairs in French that cover stereotypes in ten types of bias like gender and age. 1,467 sentence pairs are translated from CrowS-pairs and 212 are newly crowdsourced. The sentence pairs contrast stereotypes concerning underadvantaged groups with the same sentence concerning advantaged groups. We find that four widely used language models (three French, one multilingual) favor sentences that express stereotypes in most bias categories. We report on the translation process from English into French, which led to a characterization of stereotypes in CrowS-pairs including the identification of US-centric cultural traits. We offer guidelines to further extend the dataset to other languages and cultural environments.</abstract>
<identifier type="citekey">neveol-etal-2022-french</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.583</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.583/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>8521</start>
<end>8531</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than English
%A Névéol, Aurélie
%A Dupont, Yoann
%A Bezançon, Julien
%A Fort, Karën
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F neveol-etal-2022-french
%X Warning: This paper contains explicit statements of offensive stereotypes which may be upsetting. Much work on biases in natural language processing has addressed biases linked to the social and cultural experience of English speaking individuals in the United States. We seek to widen the scope of bias studies by creating material to measure social bias in language models (LMs) against specific demographic groups in France. 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. We introduce 1,679 sentence pairs in French that cover stereotypes in ten types of bias like gender and age. 1,467 sentence pairs are translated from CrowS-pairs and 212 are newly crowdsourced. The sentence pairs contrast stereotypes concerning underadvantaged groups with the same sentence concerning advantaged groups. We find that four widely used language models (three French, one multilingual) favor sentences that express stereotypes in most bias categories. We report on the translation process from English into French, which led to a characterization of stereotypes in CrowS-pairs including the identification of US-centric cultural traits. We offer guidelines to further extend the dataset to other languages and cultural environments.
%R 10.18653/v1/2022.acl-long.583
%U https://aclanthology.org/2022.acl-long.583/
%U https://doi.org/10.18653/v1/2022.acl-long.583
%P 8521-8531
Markdown (Informal)
[French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than English](https://aclanthology.org/2022.acl-long.583/) (Névéol et al., ACL 2022)
ACL