@inproceedings{nwesri-etal-2023-uot,
title = "{U}o{T} at {NADI} 2023 shared task: Automatic {A}rabic Dialect Identification is Made Possible",
author = "Nwesri, Abduslam F A and
Shinbir, Nabila A S and
Ebrahem, Hassan",
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-1.64",
doi = "10.18653/v1/2023.arabicnlp-1.64",
pages = "620--624",
abstract = "In this paper we present our approach towards Arabic Dialect identification which was part of the The Fourth Nuanced Arabic Dialect Identification Shared Task (NADI 2023). We tested several techniques to identify Arabic dialects. We obtained the best result by fine-tuning the pre-trained MARBERTv2 model with a modified training dataset. The training set was expanded by sorting tweets based on dialects, concatenating every two adjacent tweets, and adding them to the original dataset as new tweets. We achieved 82.87 on F1 score and we were at the seventh position among 16 participants.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nwesri-etal-2023-uot">
<titleInfo>
<title>UoT at NADI 2023 shared task: Automatic Arabic Dialect Identification is Made Possible</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abduslam</namePart>
<namePart type="given">F</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Nwesri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nabila</namePart>
<namePart type="given">A</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Shinbir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Ebrahem</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>In this paper we present our approach towards Arabic Dialect identification which was part of the The Fourth Nuanced Arabic Dialect Identification Shared Task (NADI 2023). We tested several techniques to identify Arabic dialects. We obtained the best result by fine-tuning the pre-trained MARBERTv2 model with a modified training dataset. The training set was expanded by sorting tweets based on dialects, concatenating every two adjacent tweets, and adding them to the original dataset as new tweets. We achieved 82.87 on F1 score and we were at the seventh position among 16 participants.</abstract>
<identifier type="citekey">nwesri-etal-2023-uot</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.64</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.64</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>620</start>
<end>624</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UoT at NADI 2023 shared task: Automatic Arabic Dialect Identification is Made Possible
%A Nwesri, Abduslam F. A.
%A Shinbir, Nabila A. S.
%A Ebrahem, Hassan
%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 nwesri-etal-2023-uot
%X In this paper we present our approach towards Arabic Dialect identification which was part of the The Fourth Nuanced Arabic Dialect Identification Shared Task (NADI 2023). We tested several techniques to identify Arabic dialects. We obtained the best result by fine-tuning the pre-trained MARBERTv2 model with a modified training dataset. The training set was expanded by sorting tweets based on dialects, concatenating every two adjacent tweets, and adding them to the original dataset as new tweets. We achieved 82.87 on F1 score and we were at the seventh position among 16 participants.
%R 10.18653/v1/2023.arabicnlp-1.64
%U https://aclanthology.org/2023.arabicnlp-1.64
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.64
%P 620-624
Markdown (Informal)
[UoT at NADI 2023 shared task: Automatic Arabic Dialect Identification is Made Possible](https://aclanthology.org/2023.arabicnlp-1.64) (Nwesri et al., ArabicNLP-WS 2023)
ACL