@inproceedings{qachfar-etal-2024-detectiveredasers,
title = "{D}etective{R}e{DAS}ers at {HSD}-2{L}ang 2024: A New Pooling Strategy with Cross-lingual Augmentation and Ensembling for Hate Speech Detection in Low-resource Languages",
author = "Qachfar, Fatima Zahra and
Tuck, Bryan and
Verma, Rakesh",
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-1.28",
pages = "199--204",
abstract = "This paper addresses hate speech detection in Turkish and Arabic tweets, contributing to the HSD-2Lang Shared Task. We propose a specialized pooling strategy within a soft-voting ensemble framework to improve classification in Turkish and Arabic language models. Our approach also includes expanding the training sets through cross-lingual translation, introducing a broader spectrum of hate speech examples. Our method attains F1-Macro scores of 0.6964 for Turkish (Subtask A) and 0.7123 for Arabic (Subtask B). While achieving these results, we also consider the computational overhead, striking a balance between the effectiveness of our unique pooling strategy, data augmentation, and soft-voting ensemble. This approach advances the practical application of language models in low-resource languages for hate speech detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qachfar-etal-2024-detectiveredasers">
<titleInfo>
<title>DetectiveReDASers at HSD-2Lang 2024: A New Pooling Strategy with Cross-lingual Augmentation and Ensembling for Hate Speech Detection in Low-resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatima</namePart>
<namePart type="given">Zahra</namePart>
<namePart type="family">Qachfar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Tuck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rakesh</namePart>
<namePart type="family">Verma</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>This paper addresses hate speech detection in Turkish and Arabic tweets, contributing to the HSD-2Lang Shared Task. We propose a specialized pooling strategy within a soft-voting ensemble framework to improve classification in Turkish and Arabic language models. Our approach also includes expanding the training sets through cross-lingual translation, introducing a broader spectrum of hate speech examples. Our method attains F1-Macro scores of 0.6964 for Turkish (Subtask A) and 0.7123 for Arabic (Subtask B). While achieving these results, we also consider the computational overhead, striking a balance between the effectiveness of our unique pooling strategy, data augmentation, and soft-voting ensemble. This approach advances the practical application of language models in low-resource languages for hate speech detection.</abstract>
<identifier type="citekey">qachfar-etal-2024-detectiveredasers</identifier>
<location>
<url>https://aclanthology.org/2024.case-1.28</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>199</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DetectiveReDASers at HSD-2Lang 2024: A New Pooling Strategy with Cross-lingual Augmentation and Ensembling for Hate Speech Detection in Low-resource Languages
%A Qachfar, Fatima Zahra
%A Tuck, Bryan
%A Verma, Rakesh
%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 qachfar-etal-2024-detectiveredasers
%X This paper addresses hate speech detection in Turkish and Arabic tweets, contributing to the HSD-2Lang Shared Task. We propose a specialized pooling strategy within a soft-voting ensemble framework to improve classification in Turkish and Arabic language models. Our approach also includes expanding the training sets through cross-lingual translation, introducing a broader spectrum of hate speech examples. Our method attains F1-Macro scores of 0.6964 for Turkish (Subtask A) and 0.7123 for Arabic (Subtask B). While achieving these results, we also consider the computational overhead, striking a balance between the effectiveness of our unique pooling strategy, data augmentation, and soft-voting ensemble. This approach advances the practical application of language models in low-resource languages for hate speech detection.
%U https://aclanthology.org/2024.case-1.28
%P 199-204
Markdown (Informal)
[DetectiveReDASers at HSD-2Lang 2024: A New Pooling Strategy with Cross-lingual Augmentation and Ensembling for Hate Speech Detection in Low-resource Languages](https://aclanthology.org/2024.case-1.28) (Qachfar et al., CASE-WS 2024)
ACL