@inproceedings{kim-etal-2022-generalizable,
title = "Generalizable Implicit Hate Speech Detection Using Contrastive Learning",
author = "Kim, Youngwook and
Park, Shinwoo and
Han, Yo-Sub",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.579",
pages = "6667--6679",
abstract = "Hate speech detection has gained increasing attention with the growing prevalence of hateful contents. When a text contains an obvious hate word or expression, it is fairly easy to detect it. However, it is challenging to identify implicit hate speech in nuance or context when there are insufficient lexical cues. Recently, there are several attempts to detect implicit hate speech leveraging pre-trained language models such as BERT and HateBERT. Fine-tuning on an implicit hate speech dataset shows satisfactory performance when evaluated on the test set of the dataset used for training. However, we empirically confirm that the performance drops at least 12.5{\%}p in F1 score when tested on the dataset that is different from the one used for training. We tackle this cross-dataset underperforming problem using contrastive learning. Based on our observation of common underlying implications in various forms of hate posts, we propose a novel contrastive learning method, ImpCon, that pulls an implication and its corresponding posts close in representation space. We evaluate the effectiveness of ImpCon by running cross-dataset evaluation on three implicit hate speech benchmarks. The experimental results on cross-dataset show that ImpCon improves at most 9.10{\%} on BERT, and 8.71{\%} on HateBERT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2022-generalizable">
<titleInfo>
<title>Generalizable Implicit Hate Speech Detection Using Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Youngwook</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinwoo</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yo-Sub</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</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">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hate speech detection has gained increasing attention with the growing prevalence of hateful contents. When a text contains an obvious hate word or expression, it is fairly easy to detect it. However, it is challenging to identify implicit hate speech in nuance or context when there are insufficient lexical cues. Recently, there are several attempts to detect implicit hate speech leveraging pre-trained language models such as BERT and HateBERT. Fine-tuning on an implicit hate speech dataset shows satisfactory performance when evaluated on the test set of the dataset used for training. However, we empirically confirm that the performance drops at least 12.5%p in F1 score when tested on the dataset that is different from the one used for training. We tackle this cross-dataset underperforming problem using contrastive learning. Based on our observation of common underlying implications in various forms of hate posts, we propose a novel contrastive learning method, ImpCon, that pulls an implication and its corresponding posts close in representation space. We evaluate the effectiveness of ImpCon by running cross-dataset evaluation on three implicit hate speech benchmarks. The experimental results on cross-dataset show that ImpCon improves at most 9.10% on BERT, and 8.71% on HateBERT.</abstract>
<identifier type="citekey">kim-etal-2022-generalizable</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.579</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>6667</start>
<end>6679</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalizable Implicit Hate Speech Detection Using Contrastive Learning
%A Kim, Youngwook
%A Park, Shinwoo
%A Han, Yo-Sub
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F kim-etal-2022-generalizable
%X Hate speech detection has gained increasing attention with the growing prevalence of hateful contents. When a text contains an obvious hate word or expression, it is fairly easy to detect it. However, it is challenging to identify implicit hate speech in nuance or context when there are insufficient lexical cues. Recently, there are several attempts to detect implicit hate speech leveraging pre-trained language models such as BERT and HateBERT. Fine-tuning on an implicit hate speech dataset shows satisfactory performance when evaluated on the test set of the dataset used for training. However, we empirically confirm that the performance drops at least 12.5%p in F1 score when tested on the dataset that is different from the one used for training. We tackle this cross-dataset underperforming problem using contrastive learning. Based on our observation of common underlying implications in various forms of hate posts, we propose a novel contrastive learning method, ImpCon, that pulls an implication and its corresponding posts close in representation space. We evaluate the effectiveness of ImpCon by running cross-dataset evaluation on three implicit hate speech benchmarks. The experimental results on cross-dataset show that ImpCon improves at most 9.10% on BERT, and 8.71% on HateBERT.
%U https://aclanthology.org/2022.coling-1.579
%P 6667-6679
Markdown (Informal)
[Generalizable Implicit Hate Speech Detection Using Contrastive Learning](https://aclanthology.org/2022.coling-1.579) (Kim et al., COLING 2022)
ACL