@inproceedings{park-etal-2023-feel,
title = "{``}Why do {I} feel offended?{''} - {K}orean Dataset for Offensive Language Identification",
author = "Park, San-Hee and
Kim, Kang-Min and
Lee, O-Joun and
Kang, Youjin and
Lee, Jaewon and
Lee, Su-Min and
Lee, SangKeun",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.85",
doi = "10.18653/v1/2023.findings-eacl.85",
pages = "1142--1153",
abstract = "Warning: This paper contains some offensive expressions. Offensive content is an unavoidable issue on social media. Most existing offensive language identification methods rely on the compilation of labeled datasets. However, existing methods rarely consider low-resource languages that have relatively less data available for training (e.g., Korean). To address these issues, we construct a novel KOrean Dataset for Offensive Language Identification (KODOLI). KODOLI comprises more fine-grained offensiveness categories (i.e., not offensive, likely offensive, and offensive) than existing ones. A likely offensive language refers to texts with implicit offensiveness or abusive language without offensive intentions. In addition, we propose two auxiliary tasks to help identify offensive languages: abusive language detection and sentiment analysis. We provide experimental results for baselines on KODOLI and observe that language models suffer from identifying {``}LIKELY{''} offensive statements. Quantitative results and qualitative analysis demonstrate that jointly learning offensive language, abusive language and sentiment information improves the performance of offensive language identification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2023-feel">
<titleInfo>
<title>“Why do I feel offended?” - Korean Dataset for Offensive Language Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">San-Hee</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang-Min</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">O-Joun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youjin</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaewon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Su-Min</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SangKeun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Warning: This paper contains some offensive expressions. Offensive content is an unavoidable issue on social media. Most existing offensive language identification methods rely on the compilation of labeled datasets. However, existing methods rarely consider low-resource languages that have relatively less data available for training (e.g., Korean). To address these issues, we construct a novel KOrean Dataset for Offensive Language Identification (KODOLI). KODOLI comprises more fine-grained offensiveness categories (i.e., not offensive, likely offensive, and offensive) than existing ones. A likely offensive language refers to texts with implicit offensiveness or abusive language without offensive intentions. In addition, we propose two auxiliary tasks to help identify offensive languages: abusive language detection and sentiment analysis. We provide experimental results for baselines on KODOLI and observe that language models suffer from identifying “LIKELY” offensive statements. Quantitative results and qualitative analysis demonstrate that jointly learning offensive language, abusive language and sentiment information improves the performance of offensive language identification.</abstract>
<identifier type="citekey">park-etal-2023-feel</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.85</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.85</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1142</start>
<end>1153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T “Why do I feel offended?” - Korean Dataset for Offensive Language Identification
%A Park, San-Hee
%A Kim, Kang-Min
%A Lee, O-Joun
%A Kang, Youjin
%A Lee, Jaewon
%A Lee, Su-Min
%A Lee, SangKeun
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F park-etal-2023-feel
%X Warning: This paper contains some offensive expressions. Offensive content is an unavoidable issue on social media. Most existing offensive language identification methods rely on the compilation of labeled datasets. However, existing methods rarely consider low-resource languages that have relatively less data available for training (e.g., Korean). To address these issues, we construct a novel KOrean Dataset for Offensive Language Identification (KODOLI). KODOLI comprises more fine-grained offensiveness categories (i.e., not offensive, likely offensive, and offensive) than existing ones. A likely offensive language refers to texts with implicit offensiveness or abusive language without offensive intentions. In addition, we propose two auxiliary tasks to help identify offensive languages: abusive language detection and sentiment analysis. We provide experimental results for baselines on KODOLI and observe that language models suffer from identifying “LIKELY” offensive statements. Quantitative results and qualitative analysis demonstrate that jointly learning offensive language, abusive language and sentiment information improves the performance of offensive language identification.
%R 10.18653/v1/2023.findings-eacl.85
%U https://aclanthology.org/2023.findings-eacl.85
%U https://doi.org/10.18653/v1/2023.findings-eacl.85
%P 1142-1153
Markdown (Informal)
[“Why do I feel offended?” - Korean Dataset for Offensive Language Identification](https://aclanthology.org/2023.findings-eacl.85) (Park et al., Findings 2023)
ACL