@inproceedings{el-sayed-etal-2023-aast,
title = "{AAST}-{NLP} at {A}r{AIE}val Shared Task: Tackling Persuasion technique and Disinformation Detection using Pre-Trained Language Models On Imbalanced Datasets",
author = "El-Sayed, Ahmed and
Nasr, Omar and
Elmadany, Noureldin",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.56",
doi = "10.18653/v1/2023.arabicnlp-1.56",
pages = "565--569",
abstract = "This paper presents the pipeline developed by the AAST-NLP team to address both the persuasion technique detection and disinformation detection shared tasks. The proposed system for all the tasks{'} sub-tasks consisted of preprocessing the data and finetuning AraBERT on the given datasets, in addition to several procedures performed for each subtask to adapt to the problems faced in it. The previously described system was used in addition to Dice loss as the loss function for sub-task 1A, which consisted of a binary classification problem. In that sub-task, the system came in eleventh place. We trained the AraBERT for task 1B, which was a multi-label problem with 24 distinct labels, using binary cross-entropy to train a classifier for each label. On that sub-task, the system came in third place. We utilised AraBERT with Dice loss on both subtasks 2A and 2B, ranking second and third among the proposed models for the respective subtasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-sayed-etal-2023-aast">
<titleInfo>
<title>AAST-NLP at ArAIEval Shared Task: Tackling Persuasion technique and Disinformation Detection using Pre-Trained Language Models On Imbalanced Datasets</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>
<name type="personal">
<namePart type="given">Noureldin</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</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">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the pipeline developed by the AAST-NLP team to address both the persuasion technique detection and disinformation detection shared tasks. The proposed system for all the tasks’ sub-tasks consisted of preprocessing the data and finetuning AraBERT on the given datasets, in addition to several procedures performed for each subtask to adapt to the problems faced in it. The previously described system was used in addition to Dice loss as the loss function for sub-task 1A, which consisted of a binary classification problem. In that sub-task, the system came in eleventh place. We trained the AraBERT for task 1B, which was a multi-label problem with 24 distinct labels, using binary cross-entropy to train a classifier for each label. On that sub-task, the system came in third place. We utilised AraBERT with Dice loss on both subtasks 2A and 2B, ranking second and third among the proposed models for the respective subtasks.</abstract>
<identifier type="citekey">el-sayed-etal-2023-aast</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.56</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.56</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>565</start>
<end>569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AAST-NLP at ArAIEval Shared Task: Tackling Persuasion technique and Disinformation Detection using Pre-Trained Language Models On Imbalanced Datasets
%A El-Sayed, Ahmed
%A Nasr, Omar
%A Elmadany, Noureldin
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F el-sayed-etal-2023-aast
%X This paper presents the pipeline developed by the AAST-NLP team to address both the persuasion technique detection and disinformation detection shared tasks. The proposed system for all the tasks’ sub-tasks consisted of preprocessing the data and finetuning AraBERT on the given datasets, in addition to several procedures performed for each subtask to adapt to the problems faced in it. The previously described system was used in addition to Dice loss as the loss function for sub-task 1A, which consisted of a binary classification problem. In that sub-task, the system came in eleventh place. We trained the AraBERT for task 1B, which was a multi-label problem with 24 distinct labels, using binary cross-entropy to train a classifier for each label. On that sub-task, the system came in third place. We utilised AraBERT with Dice loss on both subtasks 2A and 2B, ranking second and third among the proposed models for the respective subtasks.
%R 10.18653/v1/2023.arabicnlp-1.56
%U https://aclanthology.org/2023.arabicnlp-1.56
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.56
%P 565-569
Markdown (Informal)
[AAST-NLP at ArAIEval Shared Task: Tackling Persuasion technique and Disinformation Detection using Pre-Trained Language Models On Imbalanced Datasets](https://aclanthology.org/2023.arabicnlp-1.56) (El-Sayed et al., ArabicNLP-WS 2023)
ACL