@inproceedings{zhu-etal-2024-plms,
title = "Do {PLM}s and Annotators Share the Same Gender Bias? Definition, Dataset, and Framework of Contextualized Gender Bias",
author = "Zhu, Shucheng and
Du, Bingjie and
Zhao, Jishun and
Liu, Ying and
Liu, Pengyuan",
editor = "Fale{\'n}ska, Agnieszka and
Basta, Christine and
Costa-juss{\`a}, Marta and
Goldfarb-Tarrant, Seraphina and
Nozza, Debora",
booktitle = "Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.gebnlp-1.2",
pages = "20--32",
abstract = "Pre-trained language models (PLMs) have achieved success in various of natural language processing (NLP) tasks. However, PLMs also introduce some disquieting safety problems, such as gender bias. Gender bias is an extremely complex issue, because different individuals may hold disparate opinions on whether the same sentence expresses harmful bias, especially those seemingly neutral or positive. This paper first defines the concept of contextualized gender bias (CGB), which makes it easy to measure implicit gender bias in both PLMs and annotators. We then construct CGBDataset, which contains 20k natural sentences with gendered words, from Chinese news. Similar to the task of masked language models, gendered words are masked for PLMs and annotators to judge whether a male word or a female word is more suitable. Then, we introduce CGBFrame to measure the gender bias of annotators. By comparing the results measured by PLMs and annotators, we find that though there are differences on the choices made by PLMs and annotators, they show significant consistency in general.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2024-plms">
<titleInfo>
<title>Do PLMs and Annotators Share the Same Gender Bias? Definition, Dataset, and Framework of Contextualized Gender Bias</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shucheng</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingjie</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jishun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Faleńska</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="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seraphina</namePart>
<namePart type="family">Goldfarb-Tarrant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models (PLMs) have achieved success in various of natural language processing (NLP) tasks. However, PLMs also introduce some disquieting safety problems, such as gender bias. Gender bias is an extremely complex issue, because different individuals may hold disparate opinions on whether the same sentence expresses harmful bias, especially those seemingly neutral or positive. This paper first defines the concept of contextualized gender bias (CGB), which makes it easy to measure implicit gender bias in both PLMs and annotators. We then construct CGBDataset, which contains 20k natural sentences with gendered words, from Chinese news. Similar to the task of masked language models, gendered words are masked for PLMs and annotators to judge whether a male word or a female word is more suitable. Then, we introduce CGBFrame to measure the gender bias of annotators. By comparing the results measured by PLMs and annotators, we find that though there are differences on the choices made by PLMs and annotators, they show significant consistency in general.</abstract>
<identifier type="citekey">zhu-etal-2024-plms</identifier>
<location>
<url>https://aclanthology.org/2024.gebnlp-1.2</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>20</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do PLMs and Annotators Share the Same Gender Bias? Definition, Dataset, and Framework of Contextualized Gender Bias
%A Zhu, Shucheng
%A Du, Bingjie
%A Zhao, Jishun
%A Liu, Ying
%A Liu, Pengyuan
%Y Faleńska, Agnieszka
%Y Basta, Christine
%Y Costa-jussà, Marta
%Y Goldfarb-Tarrant, Seraphina
%Y Nozza, Debora
%S Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhu-etal-2024-plms
%X Pre-trained language models (PLMs) have achieved success in various of natural language processing (NLP) tasks. However, PLMs also introduce some disquieting safety problems, such as gender bias. Gender bias is an extremely complex issue, because different individuals may hold disparate opinions on whether the same sentence expresses harmful bias, especially those seemingly neutral or positive. This paper first defines the concept of contextualized gender bias (CGB), which makes it easy to measure implicit gender bias in both PLMs and annotators. We then construct CGBDataset, which contains 20k natural sentences with gendered words, from Chinese news. Similar to the task of masked language models, gendered words are masked for PLMs and annotators to judge whether a male word or a female word is more suitable. Then, we introduce CGBFrame to measure the gender bias of annotators. By comparing the results measured by PLMs and annotators, we find that though there are differences on the choices made by PLMs and annotators, they show significant consistency in general.
%U https://aclanthology.org/2024.gebnlp-1.2
%P 20-32
Markdown (Informal)
[Do PLMs and Annotators Share the Same Gender Bias? Definition, Dataset, and Framework of Contextualized Gender Bias](https://aclanthology.org/2024.gebnlp-1.2) (Zhu et al., GeBNLP-WS 2024)
ACL