@inproceedings{steinborn-etal-2022-information,
title = "An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language Models",
author = "Steinborn, Victor and
Dufter, Philipp and
Jabbar, Haris and
Schuetze, Hinrich",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.69",
doi = "10.18653/v1/2022.findings-naacl.69",
pages = "921--932",
abstract = "Bias research in NLP is a rapidly growing and developing field. Similar to CrowS-Pairs (Nangia et al., 2020), we assess gender bias in masked-language models (MLMs) by studying pairs of sentences with gender swapped person references. Most bias research focuses on and often is specific to English.Using a novel methodology for creating sentence pairs that is applicable across languages, we create, based on CrowS-Pairs, a multilingual dataset for English, Finnish, German, Indonesian and Thai.Additionally, we propose $S_{JSD}$, a new bias measure based on Jensen{--}Shannon divergence, which we argue retains more information from the model output probabilities than other previously proposed bias measures for MLMs.Using multilingual MLMs, we find that $S_{JSD}$ diagnoses the same systematic biased behavior for non-English that previous studies have found for monolingual English pre-trained MLMs. $S_{JSD}$ outperforms the CrowS-Pairs measure, which struggles to find such biases for smaller non-English datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="steinborn-etal-2022-information">
<titleInfo>
<title>An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Steinborn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Dufter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haris</namePart>
<namePart type="family">Jabbar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schuetze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bias research in NLP is a rapidly growing and developing field. Similar to CrowS-Pairs (Nangia et al., 2020), we assess gender bias in masked-language models (MLMs) by studying pairs of sentences with gender swapped person references. Most bias research focuses on and often is specific to English.Using a novel methodology for creating sentence pairs that is applicable across languages, we create, based on CrowS-Pairs, a multilingual dataset for English, Finnish, German, Indonesian and Thai.Additionally, we propose S_JSD, a new bias measure based on Jensen–Shannon divergence, which we argue retains more information from the model output probabilities than other previously proposed bias measures for MLMs.Using multilingual MLMs, we find that S_JSD diagnoses the same systematic biased behavior for non-English that previous studies have found for monolingual English pre-trained MLMs. S_JSD outperforms the CrowS-Pairs measure, which struggles to find such biases for smaller non-English datasets.</abstract>
<identifier type="citekey">steinborn-etal-2022-information</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.69</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.69</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>921</start>
<end>932</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language Models
%A Steinborn, Victor
%A Dufter, Philipp
%A Jabbar, Haris
%A Schuetze, Hinrich
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F steinborn-etal-2022-information
%X Bias research in NLP is a rapidly growing and developing field. Similar to CrowS-Pairs (Nangia et al., 2020), we assess gender bias in masked-language models (MLMs) by studying pairs of sentences with gender swapped person references. Most bias research focuses on and often is specific to English.Using a novel methodology for creating sentence pairs that is applicable across languages, we create, based on CrowS-Pairs, a multilingual dataset for English, Finnish, German, Indonesian and Thai.Additionally, we propose S_JSD, a new bias measure based on Jensen–Shannon divergence, which we argue retains more information from the model output probabilities than other previously proposed bias measures for MLMs.Using multilingual MLMs, we find that S_JSD diagnoses the same systematic biased behavior for non-English that previous studies have found for monolingual English pre-trained MLMs. S_JSD outperforms the CrowS-Pairs measure, which struggles to find such biases for smaller non-English datasets.
%R 10.18653/v1/2022.findings-naacl.69
%U https://aclanthology.org/2022.findings-naacl.69
%U https://doi.org/10.18653/v1/2022.findings-naacl.69
%P 921-932
Markdown (Informal)
[An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language Models](https://aclanthology.org/2022.findings-naacl.69) (Steinborn et al., Findings 2022)
ACL