@inproceedings{zhao-etal-2021-zhong,
title = "中文句子级性别无偏数据集构建及预训练语言模型的性别偏度评估(Construction of {C}hinese Sentence-Level Gender-Unbiased Data Set and Evaluation of Gender Bias in Pre-Training Language)",
author = "Zhao, Jishun and
Du, Bingjie and
Zhu, Shucheng and
Liu, Pengyuan",
editor = "Li, Sheng and
Sun, Maosong and
Liu, Yang and
Wu, Hua and
Liu, Kang and
Che, Wanxiang and
He, Shizhu and
Rao, Gaoqi",
booktitle = "Proceedings of the 20th Chinese National Conference on Computational Linguistics",
month = aug,
year = "2021",
address = "Huhhot, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2021.ccl-1.51",
pages = "564--575",
abstract = "自然语言处理领域各项任务中,模型广泛存在性别偏见。然而当前尚无中文性别偏见评估和消偏的相关数据集,因此无法对中文自然语言处理模型中的性别偏见进行评估。首先本文根据16对性别称谓词,从一个平面媒体语料库中筛选出性别无偏的句子,构建了一个含有20000条语句的中文句子级性别无偏数据集SlguSet。随后,本文提出了一个可衡量预训练语言模型性别偏见程度的指标,并对5种流行的预训练语言模型中的性别偏见进行评估。结果表明,中文预训练语言模型中存在不同程度的性别偏见,该文所构建数据集能够很好的对中文预训练语言模型中的性别偏见进行评估。同时,该数据集还可作为评估预训练语言模型消偏方法的数据集。",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2021-zhong">
<titleInfo>
<title>中文句子级性别无偏数据集构建及预训练语言模型的性别偏度评估(Construction of Chinese Sentence-Level Gender-Unbiased Data Set and Evaluation of Gender Bias in Pre-Training Language)</title>
</titleInfo>
<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">Bingjie</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Pengyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">Chinese</languageTerm>
<languageTerm type="code" authority="iso639-2b">chi</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Huhhot, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>自然语言处理领域各项任务中,模型广泛存在性别偏见。然而当前尚无中文性别偏见评估和消偏的相关数据集,因此无法对中文自然语言处理模型中的性别偏见进行评估。首先本文根据16对性别称谓词,从一个平面媒体语料库中筛选出性别无偏的句子,构建了一个含有20000条语句的中文句子级性别无偏数据集SlguSet。随后,本文提出了一个可衡量预训练语言模型性别偏见程度的指标,并对5种流行的预训练语言模型中的性别偏见进行评估。结果表明,中文预训练语言模型中存在不同程度的性别偏见,该文所构建数据集能够很好的对中文预训练语言模型中的性别偏见进行评估。同时,该数据集还可作为评估预训练语言模型消偏方法的数据集。</abstract>
<identifier type="citekey">zhao-etal-2021-zhong</identifier>
<location>
<url>https://aclanthology.org/2021.ccl-1.51</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>564</start>
<end>575</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 中文句子级性别无偏数据集构建及预训练语言模型的性别偏度评估(Construction of Chinese Sentence-Level Gender-Unbiased Data Set and Evaluation of Gender Bias in Pre-Training Language)
%A Zhao, Jishun
%A Du, Bingjie
%A Zhu, Shucheng
%A Liu, Pengyuan
%Y Li, Sheng
%Y Sun, Maosong
%Y Liu, Yang
%Y Wu, Hua
%Y Liu, Kang
%Y Che, Wanxiang
%Y He, Shizhu
%Y Rao, Gaoqi
%S Proceedings of the 20th Chinese National Conference on Computational Linguistics
%D 2021
%8 August
%I Chinese Information Processing Society of China
%C Huhhot, China
%G Chinese
%F zhao-etal-2021-zhong
%X 自然语言处理领域各项任务中,模型广泛存在性别偏见。然而当前尚无中文性别偏见评估和消偏的相关数据集,因此无法对中文自然语言处理模型中的性别偏见进行评估。首先本文根据16对性别称谓词,从一个平面媒体语料库中筛选出性别无偏的句子,构建了一个含有20000条语句的中文句子级性别无偏数据集SlguSet。随后,本文提出了一个可衡量预训练语言模型性别偏见程度的指标,并对5种流行的预训练语言模型中的性别偏见进行评估。结果表明,中文预训练语言模型中存在不同程度的性别偏见,该文所构建数据集能够很好的对中文预训练语言模型中的性别偏见进行评估。同时,该数据集还可作为评估预训练语言模型消偏方法的数据集。
%U https://aclanthology.org/2021.ccl-1.51
%P 564-575
Markdown (Informal)
[中文句子级性别无偏数据集构建及预训练语言模型的性别偏度评估(Construction of Chinese Sentence-Level Gender-Unbiased Data Set and Evaluation of Gender Bias in Pre-Training Language)](https://aclanthology.org/2021.ccl-1.51) (Zhao et al., CCL 2021)
ACL