@inproceedings{hoang-etal-2023-vihos,
title = "{V}i{HOS}: Hate Speech Spans Detection for {V}ietnamese",
author = "Hoang, Phu Gia and
Luu, Canh Duc and
Tran, Khanh Quoc and
Nguyen, Kiet Van and
Nguyen, Ngan Luu-Thuy",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.47/",
doi = "10.18653/v1/2023.eacl-main.47",
pages = "652--669",
abstract = "The rise in hateful and offensive language directed at other users is one of the adverse side effects of the increased use of social networking platforms. This could make it difficult for human moderators to review tagged comments filtered by classification systems. To help address this issue, we present the ViHOS (Vietnamese Hate and Offensive Spans) dataset, the first human-annotated corpus containing 26k spans on 11k comments. We also provide definitions of hateful and offensive spans in Vietnamese comments as well as detailed annotation guidelines. Besides, we conduct experiments with various state-of-the-art models. Specifically, XLM-R{\_}Large achieved the best F1-scores in Single span detection and All spans detection, while PhoBERT{\_}Large obtained the highest in Multiple spans detection. Finally, our error analysis demonstrates the difficulties in detecting specific types of spans in our data for future research. Our dataset is released on GitHub."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoang-etal-2023-vihos">
<titleInfo>
<title>ViHOS: Hate Speech Spans Detection for Vietnamese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phu</namePart>
<namePart type="given">Gia</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Canh</namePart>
<namePart type="given">Duc</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khanh</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiet</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngan</namePart>
<namePart type="given">Luu-Thuy</namePart>
<namePart type="family">Nguyen</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>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</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>The rise in hateful and offensive language directed at other users is one of the adverse side effects of the increased use of social networking platforms. This could make it difficult for human moderators to review tagged comments filtered by classification systems. To help address this issue, we present the ViHOS (Vietnamese Hate and Offensive Spans) dataset, the first human-annotated corpus containing 26k spans on 11k comments. We also provide definitions of hateful and offensive spans in Vietnamese comments as well as detailed annotation guidelines. Besides, we conduct experiments with various state-of-the-art models. Specifically, XLM-R_Large achieved the best F1-scores in Single span detection and All spans detection, while PhoBERT_Large obtained the highest in Multiple spans detection. Finally, our error analysis demonstrates the difficulties in detecting specific types of spans in our data for future research. Our dataset is released on GitHub.</abstract>
<identifier type="citekey">hoang-etal-2023-vihos</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.47</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.47/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>652</start>
<end>669</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ViHOS: Hate Speech Spans Detection for Vietnamese
%A Hoang, Phu Gia
%A Luu, Canh Duc
%A Tran, Khanh Quoc
%A Nguyen, Kiet Van
%A Nguyen, Ngan Luu-Thuy
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F hoang-etal-2023-vihos
%X The rise in hateful and offensive language directed at other users is one of the adverse side effects of the increased use of social networking platforms. This could make it difficult for human moderators to review tagged comments filtered by classification systems. To help address this issue, we present the ViHOS (Vietnamese Hate and Offensive Spans) dataset, the first human-annotated corpus containing 26k spans on 11k comments. We also provide definitions of hateful and offensive spans in Vietnamese comments as well as detailed annotation guidelines. Besides, we conduct experiments with various state-of-the-art models. Specifically, XLM-R_Large achieved the best F1-scores in Single span detection and All spans detection, while PhoBERT_Large obtained the highest in Multiple spans detection. Finally, our error analysis demonstrates the difficulties in detecting specific types of spans in our data for future research. Our dataset is released on GitHub.
%R 10.18653/v1/2023.eacl-main.47
%U https://aclanthology.org/2023.eacl-main.47/
%U https://doi.org/10.18653/v1/2023.eacl-main.47
%P 652-669
Markdown (Informal)
[ViHOS: Hate Speech Spans Detection for Vietnamese](https://aclanthology.org/2023.eacl-main.47/) (Hoang et al., EACL 2023)
ACL
- Phu Gia Hoang, Canh Duc Luu, Khanh Quoc Tran, Kiet Van Nguyen, and Ngan Luu-Thuy Nguyen. 2023. ViHOS: Hate Speech Spans Detection for Vietnamese. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 652–669, Dubrovnik, Croatia. Association for Computational Linguistics.