@inproceedings{demidova-etal-2024-arabic,
title = "{A}rabic Train at {NADI} 2024 shared task: {LLM}s{'} Ability to Translate {A}rabic Dialects into {M}odern {S}tandard {A}rabic",
author = "Demidova, Anastasiia and
Atwany, Hanin and
Rabih, Nour and
Sha{'}ban, Sanad",
editor = "Habash, Nizar and
Bouamor, Houda and
Eskander, Ramy and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Abdelali, Ahmed and
Touileb, Samia and
Hamed, Injy and
Onaizan, Yaser and
Alhafni, Bashar and
Antoun, Wissam and
Khalifa, Salam and
Haddad, Hatem and
Zitouni, Imed and
AlKhamissi, Badr and
Almatham, Rawan and
Mrini, Khalil",
booktitle = "Proceedings of The Second Arabic Natural Language Processing Conference",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.arabicnlp-1.80",
pages = "729--734",
abstract = "Navigating the intricacies of machine translation (MT) involves tackling the nuanced disparities between Arabic dialects and Modern Standard Arabic (MSA), presenting a formidable obstacle. In this study, we delve into Subtask 3 of the NADI shared task (CITATION), focusing on the translation of sentences from four distinct Arabic dialects into MSA. Our investigation explores the efficacy of various models, including Jais, NLLB, GPT-3.5, and GPT-4, in this dialect-to-MSA translation endeavor. Our findings reveal that Jais surpasses all other models, boasting an average BLEU score of 19.48 in the combination of zero- and few-shot setting, whereas NLLB exhibits the least favorable performance, garnering a BLEU score of 8.77.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="demidova-etal-2024-arabic">
<titleInfo>
<title>Arabic Train at NADI 2024 shared task: LLMs’ Ability to Translate Arabic Dialects into Modern Standard Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasiia</namePart>
<namePart type="family">Demidova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanin</namePart>
<namePart type="family">Atwany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nour</namePart>
<namePart type="family">Rabih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanad</namePart>
<namePart type="family">Sha’ban</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Second Arabic Natural Language Processing Conference</title>
</titleInfo>
<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">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</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">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</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">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">Badr</namePart>
<namePart type="family">AlKhamissi</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>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Navigating the intricacies of machine translation (MT) involves tackling the nuanced disparities between Arabic dialects and Modern Standard Arabic (MSA), presenting a formidable obstacle. In this study, we delve into Subtask 3 of the NADI shared task (CITATION), focusing on the translation of sentences from four distinct Arabic dialects into MSA. Our investigation explores the efficacy of various models, including Jais, NLLB, GPT-3.5, and GPT-4, in this dialect-to-MSA translation endeavor. Our findings reveal that Jais surpasses all other models, boasting an average BLEU score of 19.48 in the combination of zero- and few-shot setting, whereas NLLB exhibits the least favorable performance, garnering a BLEU score of 8.77.</abstract>
<identifier type="citekey">demidova-etal-2024-arabic</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.80</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>729</start>
<end>734</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Train at NADI 2024 shared task: LLMs’ Ability to Translate Arabic Dialects into Modern Standard Arabic
%A Demidova, Anastasiia
%A Atwany, Hanin
%A Rabih, Nour
%A Sha’ban, Sanad
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Eskander, Ramy
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Abdelali, Ahmed
%Y Touileb, Samia
%Y Hamed, Injy
%Y Onaizan, Yaser
%Y Alhafni, Bashar
%Y Antoun, Wissam
%Y Khalifa, Salam
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Mrini, Khalil
%S Proceedings of The Second Arabic Natural Language Processing Conference
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F demidova-etal-2024-arabic
%X Navigating the intricacies of machine translation (MT) involves tackling the nuanced disparities between Arabic dialects and Modern Standard Arabic (MSA), presenting a formidable obstacle. In this study, we delve into Subtask 3 of the NADI shared task (CITATION), focusing on the translation of sentences from four distinct Arabic dialects into MSA. Our investigation explores the efficacy of various models, including Jais, NLLB, GPT-3.5, and GPT-4, in this dialect-to-MSA translation endeavor. Our findings reveal that Jais surpasses all other models, boasting an average BLEU score of 19.48 in the combination of zero- and few-shot setting, whereas NLLB exhibits the least favorable performance, garnering a BLEU score of 8.77.
%U https://aclanthology.org/2024.arabicnlp-1.80
%P 729-734
Markdown (Informal)
[Arabic Train at NADI 2024 shared task: LLMs’ Ability to Translate Arabic Dialects into Modern Standard Arabic](https://aclanthology.org/2024.arabicnlp-1.80) (Demidova et al., ArabicNLP-WS 2024)
ACL