@inproceedings{lu-etal-2023-facilitating,
title = "Facilitating Fine-grained Detection of {C}hinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks",
author = "Lu, Junyu and
Xu, Bo and
Zhang, Xiaokun and
Min, Changrong and
Yang, Liang and
Lin, Hongfei",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.898",
doi = "10.18653/v1/2023.acl-long.898",
pages = "16235--16250",
abstract = "The widespread dissemination of toxic online posts is increasingly damaging to society. However, research on detecting toxic language in Chinese has lagged significantly due to limited datasets. Existing datasets suffer from a lack of fine-grained annotations, such as the toxic type and expressions with indirect toxicity. These fine-grained annotations are crucial factors for accurately detecting the toxicity of posts involved with lexical knowledge, which has been a challenge for researchers. To tackle this problem, we facilitate the fine-grained detection of Chinese toxic language by building a new dataset with benchmark results. First, we devised Monitor Toxic Frame, a hierarchical taxonomy to analyze the toxic type and expressions. Then, we built a fine-grained dataset ToxiCN, including both direct and indirect toxic samples. ToxiCN is based on an insulting vocabulary containing implicit profanity. We further propose a benchmark model, Toxic Knowledge Enhancement (TKE), by incorporating lexical features to detect toxic language. We demonstrate the usability of ToxiCN and the effectiveness of TKE based on a systematic quantitative and qualitative analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2023-facilitating">
<titleInfo>
<title>Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junyu</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaokun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changrong</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The widespread dissemination of toxic online posts is increasingly damaging to society. However, research on detecting toxic language in Chinese has lagged significantly due to limited datasets. Existing datasets suffer from a lack of fine-grained annotations, such as the toxic type and expressions with indirect toxicity. These fine-grained annotations are crucial factors for accurately detecting the toxicity of posts involved with lexical knowledge, which has been a challenge for researchers. To tackle this problem, we facilitate the fine-grained detection of Chinese toxic language by building a new dataset with benchmark results. First, we devised Monitor Toxic Frame, a hierarchical taxonomy to analyze the toxic type and expressions. Then, we built a fine-grained dataset ToxiCN, including both direct and indirect toxic samples. ToxiCN is based on an insulting vocabulary containing implicit profanity. We further propose a benchmark model, Toxic Knowledge Enhancement (TKE), by incorporating lexical features to detect toxic language. We demonstrate the usability of ToxiCN and the effectiveness of TKE based on a systematic quantitative and qualitative analysis.</abstract>
<identifier type="citekey">lu-etal-2023-facilitating</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.898</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.898</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>16235</start>
<end>16250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks
%A Lu, Junyu
%A Xu, Bo
%A Zhang, Xiaokun
%A Min, Changrong
%A Yang, Liang
%A Lin, Hongfei
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F lu-etal-2023-facilitating
%X The widespread dissemination of toxic online posts is increasingly damaging to society. However, research on detecting toxic language in Chinese has lagged significantly due to limited datasets. Existing datasets suffer from a lack of fine-grained annotations, such as the toxic type and expressions with indirect toxicity. These fine-grained annotations are crucial factors for accurately detecting the toxicity of posts involved with lexical knowledge, which has been a challenge for researchers. To tackle this problem, we facilitate the fine-grained detection of Chinese toxic language by building a new dataset with benchmark results. First, we devised Monitor Toxic Frame, a hierarchical taxonomy to analyze the toxic type and expressions. Then, we built a fine-grained dataset ToxiCN, including both direct and indirect toxic samples. ToxiCN is based on an insulting vocabulary containing implicit profanity. We further propose a benchmark model, Toxic Knowledge Enhancement (TKE), by incorporating lexical features to detect toxic language. We demonstrate the usability of ToxiCN and the effectiveness of TKE based on a systematic quantitative and qualitative analysis.
%R 10.18653/v1/2023.acl-long.898
%U https://aclanthology.org/2023.acl-long.898
%U https://doi.org/10.18653/v1/2023.acl-long.898
%P 16235-16250
Markdown (Informal)
[Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://aclanthology.org/2023.acl-long.898) (Lu et al., ACL 2023)
ACL
- Junyu Lu, Bo Xu, Xiaokun Zhang, Changrong Min, Liang Yang, and Hongfei Lin. 2023. Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16235–16250, Toronto, Canada. Association for Computational Linguistics.