@inproceedings{adel-elmadany-2023-isl,
title = "{ISL}-{AAST} at {NADI} 2023 shared task: Enhancing {A}rabic Dialect Identification in the Era of Globalization and Technological Progress",
author = "Adel, Shorouk 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-1.66",
doi = "10.18653/v1/2023.arabicnlp-1.66",
pages = "631--636",
abstract = "Arabic dialects have extensive global usage owing to their significance and the vast number of Arabic speakers. However, technological progress and globalization are leading to significant transformations within Arabic dialects. They are acquiring new characteristics involving novel vocabulary and integrating of linguistic elements from diverse dialects. Consequently, sentiment analysis of these dialects is becoming more challenging. This study categorizes dialects among 18 countries, as introduced by the Nuanced Arabic Dialect Identification (NADI) shared task competition. Our approach incorporates the utilization of the MARABERT and MARABERT v2 models with a range of methodologies, including a feature extraction process. Our findings reveal that the most effective model is achieved by applying averaging and concatenation to the hidden layers of MARABERT v2, followed by feeding the resulting output into convolutional layers. Furthermore, employing the ensemble method on various methods enhances the model{'}s performance. Our system secures the 6th position among the top performers in the First subtask, achieving an F1 score of 83.73{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adel-elmadany-2023-isl">
<titleInfo>
<title>ISL-AAST at NADI 2023 shared task: Enhancing Arabic Dialect Identification in the Era of Globalization and Technological Progress</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shorouk</namePart>
<namePart type="family">Adel</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>Arabic dialects have extensive global usage owing to their significance and the vast number of Arabic speakers. However, technological progress and globalization are leading to significant transformations within Arabic dialects. They are acquiring new characteristics involving novel vocabulary and integrating of linguistic elements from diverse dialects. Consequently, sentiment analysis of these dialects is becoming more challenging. This study categorizes dialects among 18 countries, as introduced by the Nuanced Arabic Dialect Identification (NADI) shared task competition. Our approach incorporates the utilization of the MARABERT and MARABERT v2 models with a range of methodologies, including a feature extraction process. Our findings reveal that the most effective model is achieved by applying averaging and concatenation to the hidden layers of MARABERT v2, followed by feeding the resulting output into convolutional layers. Furthermore, employing the ensemble method on various methods enhances the model’s performance. Our system secures the 6th position among the top performers in the First subtask, achieving an F1 score of 83.73%.</abstract>
<identifier type="citekey">adel-elmadany-2023-isl</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.66</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.66</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>631</start>
<end>636</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ISL-AAST at NADI 2023 shared task: Enhancing Arabic Dialect Identification in the Era of Globalization and Technological Progress
%A Adel, Shorouk
%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 adel-elmadany-2023-isl
%X Arabic dialects have extensive global usage owing to their significance and the vast number of Arabic speakers. However, technological progress and globalization are leading to significant transformations within Arabic dialects. They are acquiring new characteristics involving novel vocabulary and integrating of linguistic elements from diverse dialects. Consequently, sentiment analysis of these dialects is becoming more challenging. This study categorizes dialects among 18 countries, as introduced by the Nuanced Arabic Dialect Identification (NADI) shared task competition. Our approach incorporates the utilization of the MARABERT and MARABERT v2 models with a range of methodologies, including a feature extraction process. Our findings reveal that the most effective model is achieved by applying averaging and concatenation to the hidden layers of MARABERT v2, followed by feeding the resulting output into convolutional layers. Furthermore, employing the ensemble method on various methods enhances the model’s performance. Our system secures the 6th position among the top performers in the First subtask, achieving an F1 score of 83.73%.
%R 10.18653/v1/2023.arabicnlp-1.66
%U https://aclanthology.org/2023.arabicnlp-1.66
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.66
%P 631-636
Markdown (Informal)
[ISL-AAST at NADI 2023 shared task: Enhancing Arabic Dialect Identification in the Era of Globalization and Technological Progress](https://aclanthology.org/2023.arabicnlp-1.66) (Adel & Elmadany, ArabicNLP-WS 2023)
ACL