@inproceedings{limisiewicz-marecek-2022-dont,
title = "Don{'}t Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information",
author = "Limisiewicz, Tomasz and
Mare{\v{c}}ek, David",
editor = "Hardmeier, Christian and
Basta, Christine and
Costa-juss{\`a}, Marta R. and
Stanovsky, Gabriel and
Gonen, Hila",
booktitle = "Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gebnlp-1.3",
doi = "10.18653/v1/2022.gebnlp-1.3",
pages = "17--29",
abstract = "The representations in large language models contain multiple types of gender information. We focus on two types of such signals in English texts: factual gender information, which is a grammatical or semantic property, and gender bias, which is the correlation between a word and specific gender. We can disentangle the model{'}s embeddings and identify components encoding both types of information with probing. We aim to diminish the stereotypical bias in the representations while preserving the factual gender signal. Our filtering method shows that it is possible to decrease the bias of gender-neutral profession names without significant deterioration of language modeling capabilities. The findings can be applied to language generation to mitigate reliance on stereotypes while preserving gender agreement in coreferences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="limisiewicz-marecek-2022-dont">
<titleInfo>
<title>Don’t Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Limisiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Mareček</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>Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hila</namePart>
<namePart type="family">Gonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The representations in large language models contain multiple types of gender information. We focus on two types of such signals in English texts: factual gender information, which is a grammatical or semantic property, and gender bias, which is the correlation between a word and specific gender. We can disentangle the model’s embeddings and identify components encoding both types of information with probing. We aim to diminish the stereotypical bias in the representations while preserving the factual gender signal. Our filtering method shows that it is possible to decrease the bias of gender-neutral profession names without significant deterioration of language modeling capabilities. The findings can be applied to language generation to mitigate reliance on stereotypes while preserving gender agreement in coreferences.</abstract>
<identifier type="citekey">limisiewicz-marecek-2022-dont</identifier>
<identifier type="doi">10.18653/v1/2022.gebnlp-1.3</identifier>
<location>
<url>https://aclanthology.org/2022.gebnlp-1.3</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>17</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Don’t Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information
%A Limisiewicz, Tomasz
%A Mareček, David
%Y Hardmeier, Christian
%Y Basta, Christine
%Y Costa-jussà, Marta R.
%Y Stanovsky, Gabriel
%Y Gonen, Hila
%S Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F limisiewicz-marecek-2022-dont
%X The representations in large language models contain multiple types of gender information. We focus on two types of such signals in English texts: factual gender information, which is a grammatical or semantic property, and gender bias, which is the correlation between a word and specific gender. We can disentangle the model’s embeddings and identify components encoding both types of information with probing. We aim to diminish the stereotypical bias in the representations while preserving the factual gender signal. Our filtering method shows that it is possible to decrease the bias of gender-neutral profession names without significant deterioration of language modeling capabilities. The findings can be applied to language generation to mitigate reliance on stereotypes while preserving gender agreement in coreferences.
%R 10.18653/v1/2022.gebnlp-1.3
%U https://aclanthology.org/2022.gebnlp-1.3
%U https://doi.org/10.18653/v1/2022.gebnlp-1.3
%P 17-29
Markdown (Informal)
[Don’t Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information](https://aclanthology.org/2022.gebnlp-1.3) (Limisiewicz & Mareček, GeBNLP 2022)
ACL