@inproceedings{wang-markov-2024-cltl,
title = "{CLTL}@Multimodal Hate Speech Event Detection 2024: The Winning Approach to Detecting Multimodal Hate Speech and Its Targets",
author = "Wang, Yeshan and
Markov, Ilia",
editor = {H{\"u}rriyeto{\u{g}}lu, Ali and
Tanev, Hristo and
Thapa, Surendrabikram and
Uludo{\u{g}}an, G{\"o}k{\c{c}}e},
booktitle = "Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2024)",
month = mar,
year = "2024",
address = "St. Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.case-1.9",
pages = "73--78",
abstract = "In the context of the proliferation of multimodal hate speech related to the Russia-Ukraine conflict, we introduce a unified multimodal fusion system for detecting hate speech and its targets in text-embedded images. Our approach leverages the Twitter-based RoBERTa and Swin Transformer V2 models to encode textual and visual modalities, and employs the Multilayer Perceptron (MLP) fusion mechanism for classification. Our system achieved macro F1 scores of 87.27{\%} for hate speech detection and 80.05{\%} for hate speech target detection in the Multimodal Hate Speech Event Detection Challenge 2024, securing the 1st rank in both subtasks. We open-source the trained models at https://huggingface.co/Yestin-Wang",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-markov-2024-cltl">
<titleInfo>
<title>CLTL@Multimodal Hate Speech Event Detection 2024: The Winning Approach to Detecting Multimodal Hate Speech and Its Targets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yeshan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilia</namePart>
<namePart type="family">Markov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hürriyetoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hristo</namePart>
<namePart type="family">Tanev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gökçe</namePart>
<namePart type="family">Uludoğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the context of the proliferation of multimodal hate speech related to the Russia-Ukraine conflict, we introduce a unified multimodal fusion system for detecting hate speech and its targets in text-embedded images. Our approach leverages the Twitter-based RoBERTa and Swin Transformer V2 models to encode textual and visual modalities, and employs the Multilayer Perceptron (MLP) fusion mechanism for classification. Our system achieved macro F1 scores of 87.27% for hate speech detection and 80.05% for hate speech target detection in the Multimodal Hate Speech Event Detection Challenge 2024, securing the 1st rank in both subtasks. We open-source the trained models at https://huggingface.co/Yestin-Wang</abstract>
<identifier type="citekey">wang-markov-2024-cltl</identifier>
<location>
<url>https://aclanthology.org/2024.case-1.9</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>73</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLTL@Multimodal Hate Speech Event Detection 2024: The Winning Approach to Detecting Multimodal Hate Speech and Its Targets
%A Wang, Yeshan
%A Markov, Ilia
%Y Hürriyetoğlu, Ali
%Y Tanev, Hristo
%Y Thapa, Surendrabikram
%Y Uludoğan, Gökçe
%S Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julians, Malta
%F wang-markov-2024-cltl
%X In the context of the proliferation of multimodal hate speech related to the Russia-Ukraine conflict, we introduce a unified multimodal fusion system for detecting hate speech and its targets in text-embedded images. Our approach leverages the Twitter-based RoBERTa and Swin Transformer V2 models to encode textual and visual modalities, and employs the Multilayer Perceptron (MLP) fusion mechanism for classification. Our system achieved macro F1 scores of 87.27% for hate speech detection and 80.05% for hate speech target detection in the Multimodal Hate Speech Event Detection Challenge 2024, securing the 1st rank in both subtasks. We open-source the trained models at https://huggingface.co/Yestin-Wang
%U https://aclanthology.org/2024.case-1.9
%P 73-78
Markdown (Informal)
[CLTL@Multimodal Hate Speech Event Detection 2024: The Winning Approach to Detecting Multimodal Hate Speech and Its Targets](https://aclanthology.org/2024.case-1.9) (Wang & Markov, CASE-WS 2024)
ACL