@inproceedings{el-sayed-nasr-2024-aast-nlp,
title = "{AAST}-{NLP} at Multimodal Hate Speech Event Detection 2024 : A Multimodal Approach for Classification of Text-Embedded Images Based on {CLIP} and {BERT}-Based Models.",
author = "El-Sayed, Ahmed and
Nasr, Omar",
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-1.19",
pages = "139--144",
abstract = "With the rapid rise of social media platforms, communities have been able to share their passions and interests with the world much more conveniently. This, in turn, has led to individuals being able to spread hateful messages through the use of memes. The classification of such materials requires not only looking at the individual images but also considering the associated text in tandem. Looking at the images or the text separately does not provide the full context. In this paper, we describe our approach to hateful meme classification for the Multimodal Hate Speech Shared Task at CASE 2024. We utilized the same approach in the two subtasks, which involved a classification model based on text and image features obtained using Contrastive Language-Image Pre-training (CLIP) in addition to utilizing BERT-Based models. We then utilize predictions created by both models in an ensemble approach. This approach ranked second in both subtasks, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-sayed-nasr-2024-aast-nlp">
<titleInfo>
<title>AAST-NLP at Multimodal Hate Speech Event Detection 2024 : A Multimodal Approach for Classification of Text-Embedded Images Based on CLIP and BERT-Based Models.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">El-Sayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Nasr</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>With the rapid rise of social media platforms, communities have been able to share their passions and interests with the world much more conveniently. This, in turn, has led to individuals being able to spread hateful messages through the use of memes. The classification of such materials requires not only looking at the individual images but also considering the associated text in tandem. Looking at the images or the text separately does not provide the full context. In this paper, we describe our approach to hateful meme classification for the Multimodal Hate Speech Shared Task at CASE 2024. We utilized the same approach in the two subtasks, which involved a classification model based on text and image features obtained using Contrastive Language-Image Pre-training (CLIP) in addition to utilizing BERT-Based models. We then utilize predictions created by both models in an ensemble approach. This approach ranked second in both subtasks, respectively.</abstract>
<identifier type="citekey">el-sayed-nasr-2024-aast-nlp</identifier>
<location>
<url>https://aclanthology.org/2024.case-1.19</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>139</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AAST-NLP at Multimodal Hate Speech Event Detection 2024 : A Multimodal Approach for Classification of Text-Embedded Images Based on CLIP and BERT-Based Models.
%A El-Sayed, Ahmed
%A Nasr, Omar
%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 el-sayed-nasr-2024-aast-nlp
%X With the rapid rise of social media platforms, communities have been able to share their passions and interests with the world much more conveniently. This, in turn, has led to individuals being able to spread hateful messages through the use of memes. The classification of such materials requires not only looking at the individual images but also considering the associated text in tandem. Looking at the images or the text separately does not provide the full context. In this paper, we describe our approach to hateful meme classification for the Multimodal Hate Speech Shared Task at CASE 2024. We utilized the same approach in the two subtasks, which involved a classification model based on text and image features obtained using Contrastive Language-Image Pre-training (CLIP) in addition to utilizing BERT-Based models. We then utilize predictions created by both models in an ensemble approach. This approach ranked second in both subtasks, respectively.
%U https://aclanthology.org/2024.case-1.19
%P 139-144
Markdown (Informal)
[AAST-NLP at Multimodal Hate Speech Event Detection 2024 : A Multimodal Approach for Classification of Text-Embedded Images Based on CLIP and BERT-Based Models.](https://aclanthology.org/2024.case-1.19) (El-Sayed & Nasr, CASE-WS 2024)
ACL