@inproceedings{kim-etal-2023-conprompt,
title = "{C}on{P}rompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection",
author = "Kim, Youngwook and
Park, Shinwoo and
Namgoong, Youngsoo and
Han, Yo-Sub",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.731/",
doi = "10.18653/v1/2023.findings-emnlp.731",
pages = "10964--10980",
abstract = "Implicit hate speech detection is a challenging task in text classification since no explicit cues (e.g., swear words) exist in the text. While some pre-trained language models have been developed for hate speech detection, they are not specialized in implicit hate speech. Recently, an implicit hate speech dataset with a massive number of samples has been proposed by controlling machine generation. We propose a pre-training approach, ConPrompt, to fully leverage such machine-generated data. Specifically, given a machine-generated statement, we use example statements of its origin prompt as positive samples for contrastive learning. Through pre-training with ConPrompt, we present ToxiGen-ConPrompt, a pre-trained language model for implicit hate speech detection. We conduct extensive experiments on several implicit hate speech datasets and show the superior generalization ability of ToxiGen-ConPrompt compared to other pre-trained models. Additionally, we empirically show that ConPrompt is effective in mitigating identity term bias, demonstrating that it not only makes a model more generalizable but also reduces unintended bias. We analyze the representation quality of ToxiGen-ConPrompt and show its ability to consider target group and toxicity, which are desirable features in terms of implicit hate speeches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2023-conprompt">
<titleInfo>
<title>ConPrompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection</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">Youngsoo</namePart>
<namePart type="family">Namgoong</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>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Implicit hate speech detection is a challenging task in text classification since no explicit cues (e.g., swear words) exist in the text. While some pre-trained language models have been developed for hate speech detection, they are not specialized in implicit hate speech. Recently, an implicit hate speech dataset with a massive number of samples has been proposed by controlling machine generation. We propose a pre-training approach, ConPrompt, to fully leverage such machine-generated data. Specifically, given a machine-generated statement, we use example statements of its origin prompt as positive samples for contrastive learning. Through pre-training with ConPrompt, we present ToxiGen-ConPrompt, a pre-trained language model for implicit hate speech detection. We conduct extensive experiments on several implicit hate speech datasets and show the superior generalization ability of ToxiGen-ConPrompt compared to other pre-trained models. Additionally, we empirically show that ConPrompt is effective in mitigating identity term bias, demonstrating that it not only makes a model more generalizable but also reduces unintended bias. We analyze the representation quality of ToxiGen-ConPrompt and show its ability to consider target group and toxicity, which are desirable features in terms of implicit hate speeches.</abstract>
<identifier type="citekey">kim-etal-2023-conprompt</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.731</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.731/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10964</start>
<end>10980</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConPrompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection
%A Kim, Youngwook
%A Park, Shinwoo
%A Namgoong, Youngsoo
%A Han, Yo-Sub
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F kim-etal-2023-conprompt
%X Implicit hate speech detection is a challenging task in text classification since no explicit cues (e.g., swear words) exist in the text. While some pre-trained language models have been developed for hate speech detection, they are not specialized in implicit hate speech. Recently, an implicit hate speech dataset with a massive number of samples has been proposed by controlling machine generation. We propose a pre-training approach, ConPrompt, to fully leverage such machine-generated data. Specifically, given a machine-generated statement, we use example statements of its origin prompt as positive samples for contrastive learning. Through pre-training with ConPrompt, we present ToxiGen-ConPrompt, a pre-trained language model for implicit hate speech detection. We conduct extensive experiments on several implicit hate speech datasets and show the superior generalization ability of ToxiGen-ConPrompt compared to other pre-trained models. Additionally, we empirically show that ConPrompt is effective in mitigating identity term bias, demonstrating that it not only makes a model more generalizable but also reduces unintended bias. We analyze the representation quality of ToxiGen-ConPrompt and show its ability to consider target group and toxicity, which are desirable features in terms of implicit hate speeches.
%R 10.18653/v1/2023.findings-emnlp.731
%U https://aclanthology.org/2023.findings-emnlp.731/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.731
%P 10964-10980
Markdown (Informal)
[ConPrompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection](https://aclanthology.org/2023.findings-emnlp.731/) (Kim et al., Findings 2023)
ACL