@inproceedings{deshpande-etal-2022-stereokg,
title = "{S}tereo{KG}: Data-Driven Knowledge Graph Construction For Cultural Knowledge and Stereotypes",
author = "Deshpande, Awantee and
Ruiter, Dana and
Mosbach, Marius and
Klakow, Dietrich",
editor = "Narang, Kanika and
Mostafazadeh Davani, Aida and
Mathias, Lambert and
Vidgen, Bertie and
Talat, Zeerak",
booktitle = "Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)",
month = jul,
year = "2022",
address = "Seattle, Washington (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.woah-1.7",
doi = "10.18653/v1/2022.woah-1.7",
pages = "67--78",
abstract = "Analyzing ethnic or religious bias is important for improving fairness, accountability, and transparency of natural language processing models. However, many techniques rely on human-compiled lists of bias terms, which are expensive to create and are limited in coverage. In this study, we present a fully data-driven pipeline for generating a knowledge graph (KG) of cultural knowledge and stereotypes. Our resulting KG covers 5 religious groups and 5 nationalities and can easily be extended to more entities. Our human evaluation shows that the majority (59.2{\%}) of non-singleton entries are coherent and complete stereotypes. We further show that performing intermediate masked language model training on the verbalized KG leads to a higher level of cultural awareness in the model and has the potential to increase classification performance on knowledge-crucial samples on a related task, i.e., hate speech detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deshpande-etal-2022-stereokg">
<titleInfo>
<title>StereoKG: Data-Driven Knowledge Graph Construction For Cultural Knowledge and Stereotypes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Awantee</namePart>
<namePart type="family">Deshpande</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Ruiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marius</namePart>
<namePart type="family">Mosbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</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 Sixth Workshop on Online Abuse and Harms (WOAH)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanika</namePart>
<namePart type="family">Narang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lambert</namePart>
<namePart type="family">Mathias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bertie</namePart>
<namePart type="family">Vidgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Analyzing ethnic or religious bias is important for improving fairness, accountability, and transparency of natural language processing models. However, many techniques rely on human-compiled lists of bias terms, which are expensive to create and are limited in coverage. In this study, we present a fully data-driven pipeline for generating a knowledge graph (KG) of cultural knowledge and stereotypes. Our resulting KG covers 5 religious groups and 5 nationalities and can easily be extended to more entities. Our human evaluation shows that the majority (59.2%) of non-singleton entries are coherent and complete stereotypes. We further show that performing intermediate masked language model training on the verbalized KG leads to a higher level of cultural awareness in the model and has the potential to increase classification performance on knowledge-crucial samples on a related task, i.e., hate speech detection.</abstract>
<identifier type="citekey">deshpande-etal-2022-stereokg</identifier>
<identifier type="doi">10.18653/v1/2022.woah-1.7</identifier>
<location>
<url>https://aclanthology.org/2022.woah-1.7</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>67</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T StereoKG: Data-Driven Knowledge Graph Construction For Cultural Knowledge and Stereotypes
%A Deshpande, Awantee
%A Ruiter, Dana
%A Mosbach, Marius
%A Klakow, Dietrich
%Y Narang, Kanika
%Y Mostafazadeh Davani, Aida
%Y Mathias, Lambert
%Y Vidgen, Bertie
%Y Talat, Zeerak
%S Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington (Hybrid)
%F deshpande-etal-2022-stereokg
%X Analyzing ethnic or religious bias is important for improving fairness, accountability, and transparency of natural language processing models. However, many techniques rely on human-compiled lists of bias terms, which are expensive to create and are limited in coverage. In this study, we present a fully data-driven pipeline for generating a knowledge graph (KG) of cultural knowledge and stereotypes. Our resulting KG covers 5 religious groups and 5 nationalities and can easily be extended to more entities. Our human evaluation shows that the majority (59.2%) of non-singleton entries are coherent and complete stereotypes. We further show that performing intermediate masked language model training on the verbalized KG leads to a higher level of cultural awareness in the model and has the potential to increase classification performance on knowledge-crucial samples on a related task, i.e., hate speech detection.
%R 10.18653/v1/2022.woah-1.7
%U https://aclanthology.org/2022.woah-1.7
%U https://doi.org/10.18653/v1/2022.woah-1.7
%P 67-78
Markdown (Informal)
[StereoKG: Data-Driven Knowledge Graph Construction For Cultural Knowledge and Stereotypes](https://aclanthology.org/2022.woah-1.7) (Deshpande et al., WOAH 2022)
ACL