@inproceedings{mostafa-etal-2022-gof,
title = "{GOF} at {A}rabic Hate Speech 2022: Breaking The Loss Function Convention For Data-Imbalanced {A}rabic Offensive Text Detection",
author = "Mostafa, Ali and
Mohamed, Omar and
Ashraf, Ali",
editor = "Al-Khalifa, Hend and
Elsayed, Tamer and
Mubarak, Hamdy and
Al-Thubaity, Abdulmohsen and
Magdy, Walid and
Darwish, Kareem",
booktitle = "Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.osact-1.21",
pages = "167--175",
abstract = "With the rise of social media platforms, we need to ensure that all users have a secure online experience by eliminating and identifying offensive language and hate speech. Furthermore, detecting such content is challenging, particularly in the Arabic language, due to a number of challenges and limitations. In general, one of the most challenging issues in real-world datasets is long-tailed data distribution. We report our submission to the Offensive Language and hate-speech Detection shared task organized with the 5th Workshop on Open-Source Arabic Corpora and Processing Tools Arabic (OSACT5); in our approach, we focused on how to overcome such a problem by experimenting with alternative loss functions rather than using the traditional weighted cross-entropy loss. Finally, we evaluated various pre-trained deep learning models using the suggested loss functions to determine the optimal model. On the development and test sets, our final model achieved 86.97{\%} and 85.17{\%}, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mostafa-etal-2022-gof">
<titleInfo>
<title>GOF at Arabic Hate Speech 2022: Breaking The Loss Function Convention For Data-Imbalanced Arabic Offensive Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Mostafa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Ashraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulmohsen</namePart>
<namePart type="family">Al-Thubaity</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the rise of social media platforms, we need to ensure that all users have a secure online experience by eliminating and identifying offensive language and hate speech. Furthermore, detecting such content is challenging, particularly in the Arabic language, due to a number of challenges and limitations. In general, one of the most challenging issues in real-world datasets is long-tailed data distribution. We report our submission to the Offensive Language and hate-speech Detection shared task organized with the 5th Workshop on Open-Source Arabic Corpora and Processing Tools Arabic (OSACT5); in our approach, we focused on how to overcome such a problem by experimenting with alternative loss functions rather than using the traditional weighted cross-entropy loss. Finally, we evaluated various pre-trained deep learning models using the suggested loss functions to determine the optimal model. On the development and test sets, our final model achieved 86.97% and 85.17%, respectively.</abstract>
<identifier type="citekey">mostafa-etal-2022-gof</identifier>
<location>
<url>https://aclanthology.org/2022.osact-1.21</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>167</start>
<end>175</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GOF at Arabic Hate Speech 2022: Breaking The Loss Function Convention For Data-Imbalanced Arabic Offensive Text Detection
%A Mostafa, Ali
%A Mohamed, Omar
%A Ashraf, Ali
%Y Al-Khalifa, Hend
%Y Elsayed, Tamer
%Y Mubarak, Hamdy
%Y Al-Thubaity, Abdulmohsen
%Y Magdy, Walid
%Y Darwish, Kareem
%S Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F mostafa-etal-2022-gof
%X With the rise of social media platforms, we need to ensure that all users have a secure online experience by eliminating and identifying offensive language and hate speech. Furthermore, detecting such content is challenging, particularly in the Arabic language, due to a number of challenges and limitations. In general, one of the most challenging issues in real-world datasets is long-tailed data distribution. We report our submission to the Offensive Language and hate-speech Detection shared task organized with the 5th Workshop on Open-Source Arabic Corpora and Processing Tools Arabic (OSACT5); in our approach, we focused on how to overcome such a problem by experimenting with alternative loss functions rather than using the traditional weighted cross-entropy loss. Finally, we evaluated various pre-trained deep learning models using the suggested loss functions to determine the optimal model. On the development and test sets, our final model achieved 86.97% and 85.17%, respectively.
%U https://aclanthology.org/2022.osact-1.21
%P 167-175
Markdown (Informal)
[GOF at Arabic Hate Speech 2022: Breaking The Loss Function Convention For Data-Imbalanced Arabic Offensive Text Detection](https://aclanthology.org/2022.osact-1.21) (Mostafa et al., OSACT 2022)
ACL