@inproceedings{li-etal-2022-herb,
title = "{HERB}: Measuring Hierarchical Regional Bias in Pre-trained Language Models",
author = "Li, Yizhi and
Zhang, Ge and
Yang, Bohao and
Lin, Chenghua and
Ragni, Anton and
Wang, Shi and
Fu, Jie",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.32",
doi = "10.18653/v1/2022.findings-aacl.32",
pages = "334--346",
abstract = "Fairness has become a trending topic in natural language processing (NLP) and covers biases targeting certain social groups such as genders and religions. Yet regional bias, another long-standing global discrimination problem, remains unexplored still. Consequently, we intend to provide a study to analyse the regional bias learned by the pre-trained language models (LMs) that are broadly used in NLP tasks. While verifying the existence of regional bias in LMs, we find that the biases on regional groups can be largely affected by the corresponding geographical clustering. We accordingly propose a hierarchical regional bias evaluation method (HERB) utilising the information from the sub-region clusters to quantify the bias in the pre-trained LMs. Experiments show that our hierarchical metric can effectively evaluate the regional bias with regard to comprehensive topics and measure the potential regional bias that can be propagated to downstream tasks. Our codes are available at \url{https://github.com/Bernard-Yang/HERB}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-herb">
<titleInfo>
<title>HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yizhi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ge</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bohao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anton</namePart>
<namePart type="family">Ragni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</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">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fairness has become a trending topic in natural language processing (NLP) and covers biases targeting certain social groups such as genders and religions. Yet regional bias, another long-standing global discrimination problem, remains unexplored still. Consequently, we intend to provide a study to analyse the regional bias learned by the pre-trained language models (LMs) that are broadly used in NLP tasks. While verifying the existence of regional bias in LMs, we find that the biases on regional groups can be largely affected by the corresponding geographical clustering. We accordingly propose a hierarchical regional bias evaluation method (HERB) utilising the information from the sub-region clusters to quantify the bias in the pre-trained LMs. Experiments show that our hierarchical metric can effectively evaluate the regional bias with regard to comprehensive topics and measure the potential regional bias that can be propagated to downstream tasks. Our codes are available at https://github.com/Bernard-Yang/HERB.</abstract>
<identifier type="citekey">li-etal-2022-herb</identifier>
<identifier type="doi">10.18653/v1/2022.findings-aacl.32</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.32</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>334</start>
<end>346</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models
%A Li, Yizhi
%A Zhang, Ge
%A Yang, Bohao
%A Lin, Chenghua
%A Ragni, Anton
%A Wang, Shi
%A Fu, Jie
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F li-etal-2022-herb
%X Fairness has become a trending topic in natural language processing (NLP) and covers biases targeting certain social groups such as genders and religions. Yet regional bias, another long-standing global discrimination problem, remains unexplored still. Consequently, we intend to provide a study to analyse the regional bias learned by the pre-trained language models (LMs) that are broadly used in NLP tasks. While verifying the existence of regional bias in LMs, we find that the biases on regional groups can be largely affected by the corresponding geographical clustering. We accordingly propose a hierarchical regional bias evaluation method (HERB) utilising the information from the sub-region clusters to quantify the bias in the pre-trained LMs. Experiments show that our hierarchical metric can effectively evaluate the regional bias with regard to comprehensive topics and measure the potential regional bias that can be propagated to downstream tasks. Our codes are available at https://github.com/Bernard-Yang/HERB.
%R 10.18653/v1/2022.findings-aacl.32
%U https://aclanthology.org/2022.findings-aacl.32
%U https://doi.org/10.18653/v1/2022.findings-aacl.32
%P 334-346
Markdown (Informal)
[HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models](https://aclanthology.org/2022.findings-aacl.32) (Li et al., Findings 2022)
ACL