@inproceedings{park-etal-2024-contrastive,
title = "Contrastive Learning as a Polarizer: Mitigating Gender Bias by Fair and Biased sentences",
author = "Park, Kyungmin and
Oh, Sihyun and
Kim, Daehyun and
Kim, Juae",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.293",
doi = "10.18653/v1/2024.findings-naacl.293",
pages = "4725--4736",
abstract = "Recently, language models have accelerated the improvement in natural language processing. However, recent studies have highlighted a significant issue: social biases inherent in training data can lead models to learn and propagate these biases. In this study, we propose a contrastive learning method for bias mitigation, utilizing anchor points to push further negatives and pull closer positives within the representation space. This approach employs stereotypical data as negatives and stereotype-free data as positives, enhancing debiasing performance. Our model attained state-of-the-art performance in the ICAT score on the StereoSet, a benchmark for measuring bias in models. In addition, we observed that effective debiasing is achieved through an awareness of biases, as evidenced by improved hate speech detection scores. The implementation code and trained models are available at https://github.com/HUFS-NLP/CL{\_}Polarizer.git.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2024-contrastive">
<titleInfo>
<title>Contrastive Learning as a Polarizer: Mitigating Gender Bias by Fair and Biased sentences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyungmin</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sihyun</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daehyun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juae</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, language models have accelerated the improvement in natural language processing. However, recent studies have highlighted a significant issue: social biases inherent in training data can lead models to learn and propagate these biases. In this study, we propose a contrastive learning method for bias mitigation, utilizing anchor points to push further negatives and pull closer positives within the representation space. This approach employs stereotypical data as negatives and stereotype-free data as positives, enhancing debiasing performance. Our model attained state-of-the-art performance in the ICAT score on the StereoSet, a benchmark for measuring bias in models. In addition, we observed that effective debiasing is achieved through an awareness of biases, as evidenced by improved hate speech detection scores. The implementation code and trained models are available at https://github.com/HUFS-NLP/CL_Polarizer.git.</abstract>
<identifier type="citekey">park-etal-2024-contrastive</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.293</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.293</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>4725</start>
<end>4736</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contrastive Learning as a Polarizer: Mitigating Gender Bias by Fair and Biased sentences
%A Park, Kyungmin
%A Oh, Sihyun
%A Kim, Daehyun
%A Kim, Juae
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F park-etal-2024-contrastive
%X Recently, language models have accelerated the improvement in natural language processing. However, recent studies have highlighted a significant issue: social biases inherent in training data can lead models to learn and propagate these biases. In this study, we propose a contrastive learning method for bias mitigation, utilizing anchor points to push further negatives and pull closer positives within the representation space. This approach employs stereotypical data as negatives and stereotype-free data as positives, enhancing debiasing performance. Our model attained state-of-the-art performance in the ICAT score on the StereoSet, a benchmark for measuring bias in models. In addition, we observed that effective debiasing is achieved through an awareness of biases, as evidenced by improved hate speech detection scores. The implementation code and trained models are available at https://github.com/HUFS-NLP/CL_Polarizer.git.
%R 10.18653/v1/2024.findings-naacl.293
%U https://aclanthology.org/2024.findings-naacl.293
%U https://doi.org/10.18653/v1/2024.findings-naacl.293
%P 4725-4736
Markdown (Informal)
[Contrastive Learning as a Polarizer: Mitigating Gender Bias by Fair and Biased sentences](https://aclanthology.org/2024.findings-naacl.293) (Park et al., Findings 2024)
ACL