@inproceedings{khered-etal-2023-unimanc,
title = "{U}ni{M}anc at {NADI} 2023 Shared Task: A Comparison of Various T5-based Models for Translating {A}rabic Dialectical Text to {M}odern {S}tandard {A}rabic",
author = "Khered, Abdullah and
Abdelhalim, Ingy and
Abdelhalim, Nadine and
Soliman, Ahmed and
Batista-Navarro, Riza",
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-1.71",
doi = "10.18653/v1/2023.arabicnlp-1.71",
pages = "658--664",
abstract = "This paper presents the methods we developed for the Nuanced Arabic Dialect Identification (NADI) 2023 shared task, specifically targeting the two subtasks focussed on sentence-level machine translation (MT) of text written in any of four Arabic dialects (Egyptian, Emirati, Jordanian and Palestinian) to Modern Standard Arabic (MSA). Our team, UniManc, employed models based on T5: multilingual T5 (mT5), multi-task fine-tuned mT5 (mT0) and AraT5. These models were trained based on two configurations: joint model training for all regional dialects (J-R) and independent model training for every regional dialect (I-R). Based on the results of the official NADI 2023 evaluation, our I-R AraT5 model obtained an overall BLEU score of 14.76, ranking first in the Closed Dialect-to-MSA MT subtask. Moreover, in the Open Dialect-to-MSA MT subtask, our J-R AraT5 model also ranked first, obtaining an overall BLEU score of 21.10.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khered-etal-2023-unimanc">
<titleInfo>
<title>UniManc at NADI 2023 Shared Task: A Comparison of Various T5-based Models for Translating Arabic Dialectical Text to Modern Standard Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Khered</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingy</namePart>
<namePart type="family">Abdelhalim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadine</namePart>
<namePart type="family">Abdelhalim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Soliman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riza</namePart>
<namePart type="family">Batista-Navarro</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 methods we developed for the Nuanced Arabic Dialect Identification (NADI) 2023 shared task, specifically targeting the two subtasks focussed on sentence-level machine translation (MT) of text written in any of four Arabic dialects (Egyptian, Emirati, Jordanian and Palestinian) to Modern Standard Arabic (MSA). Our team, UniManc, employed models based on T5: multilingual T5 (mT5), multi-task fine-tuned mT5 (mT0) and AraT5. These models were trained based on two configurations: joint model training for all regional dialects (J-R) and independent model training for every regional dialect (I-R). Based on the results of the official NADI 2023 evaluation, our I-R AraT5 model obtained an overall BLEU score of 14.76, ranking first in the Closed Dialect-to-MSA MT subtask. Moreover, in the Open Dialect-to-MSA MT subtask, our J-R AraT5 model also ranked first, obtaining an overall BLEU score of 21.10.</abstract>
<identifier type="citekey">khered-etal-2023-unimanc</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.71</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.71</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>658</start>
<end>664</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UniManc at NADI 2023 Shared Task: A Comparison of Various T5-based Models for Translating Arabic Dialectical Text to Modern Standard Arabic
%A Khered, Abdullah
%A Abdelhalim, Ingy
%A Abdelhalim, Nadine
%A Soliman, Ahmed
%A Batista-Navarro, Riza
%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 khered-etal-2023-unimanc
%X This paper presents the methods we developed for the Nuanced Arabic Dialect Identification (NADI) 2023 shared task, specifically targeting the two subtasks focussed on sentence-level machine translation (MT) of text written in any of four Arabic dialects (Egyptian, Emirati, Jordanian and Palestinian) to Modern Standard Arabic (MSA). Our team, UniManc, employed models based on T5: multilingual T5 (mT5), multi-task fine-tuned mT5 (mT0) and AraT5. These models were trained based on two configurations: joint model training for all regional dialects (J-R) and independent model training for every regional dialect (I-R). Based on the results of the official NADI 2023 evaluation, our I-R AraT5 model obtained an overall BLEU score of 14.76, ranking first in the Closed Dialect-to-MSA MT subtask. Moreover, in the Open Dialect-to-MSA MT subtask, our J-R AraT5 model also ranked first, obtaining an overall BLEU score of 21.10.
%R 10.18653/v1/2023.arabicnlp-1.71
%U https://aclanthology.org/2023.arabicnlp-1.71
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.71
%P 658-664
Markdown (Informal)
[UniManc at NADI 2023 Shared Task: A Comparison of Various T5-based Models for Translating Arabic Dialectical Text to Modern Standard Arabic](https://aclanthology.org/2023.arabicnlp-1.71) (Khered et al., ArabicNLP-WS 2023)
ACL