@inproceedings{khered-etal-2025-multi,
title = "A Multi-Task Learning Approach to Dialectal {A}rabic Identification and Translation to {M}odern {S}tandard {A}rabic",
author = "Khered, Abdullah and
Benkhedda, Youcef and
Batista-Navarro, Riza",
editor = "Estevanell-Valladares, Ernesto Luis and
Picazo-Izquierdo, Alicia and
Ranasinghe, Tharindu and
Mikaberidze, Besik and
Ostermann, Simon and
Gurgurov, Daniil and
Mueller, Philipp and
Borg, Claudia and
{\v{S}}imko, Mari{\'a}n",
booktitle = "Proceedings of the First Workshop on Advancing {NLP} for Low-Resource Languages",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.lowresnlp-1.4/",
pages = "21--31",
abstract = "Translating Dialectal Arabic (DA) into Modern Standard Arabic (MSA) is a complex task due to the linguistic diversity and informal nature of dialects, particularly in social media texts. To improve translation quality, we propose a Multi-Task Learning (MTL) framework that combines DA-MSA translation as the primary task and dialect identification as an auxiliary task. Additionally, we introduce LahjaTube, a new corpus containing DA transcripts and corresponding MSA and English translations, covering four major Arabic dialects: Egyptian (EGY), Gulf (GLF), Levantine (LEV), and Maghrebi (MGR), collected from YouTube. We evaluate AraT5 and AraBART on the Dial2MSA-Verified dataset under Single-Task Learning (STL) and MTL setups. Our results show that adopting the MTL framework and incorporating LahjaTube into the training data improve the translation performance, leading to a BLEU score improvement of 2.65 points over baseline models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khered-etal-2025-multi">
<titleInfo>
<title>A Multi-Task Learning Approach to Dialectal Arabic Identification and Translation 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">Youcef</namePart>
<namePart type="family">Benkhedda</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>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Estevanell-Valladares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Picazo-Izquierdo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Besik</namePart>
<namePart type="family">Mikaberidze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Ostermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniil</namePart>
<namePart type="family">Gurgurov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Borg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marián</namePart>
<namePart type="family">Šimko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translating Dialectal Arabic (DA) into Modern Standard Arabic (MSA) is a complex task due to the linguistic diversity and informal nature of dialects, particularly in social media texts. To improve translation quality, we propose a Multi-Task Learning (MTL) framework that combines DA-MSA translation as the primary task and dialect identification as an auxiliary task. Additionally, we introduce LahjaTube, a new corpus containing DA transcripts and corresponding MSA and English translations, covering four major Arabic dialects: Egyptian (EGY), Gulf (GLF), Levantine (LEV), and Maghrebi (MGR), collected from YouTube. We evaluate AraT5 and AraBART on the Dial2MSA-Verified dataset under Single-Task Learning (STL) and MTL setups. Our results show that adopting the MTL framework and incorporating LahjaTube into the training data improve the translation performance, leading to a BLEU score improvement of 2.65 points over baseline models.</abstract>
<identifier type="citekey">khered-etal-2025-multi</identifier>
<location>
<url>https://aclanthology.org/2025.lowresnlp-1.4/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>21</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multi-Task Learning Approach to Dialectal Arabic Identification and Translation to Modern Standard Arabic
%A Khered, Abdullah
%A Benkhedda, Youcef
%A Batista-Navarro, Riza
%Y Estevanell-Valladares, Ernesto Luis
%Y Picazo-Izquierdo, Alicia
%Y Ranasinghe, Tharindu
%Y Mikaberidze, Besik
%Y Ostermann, Simon
%Y Gurgurov, Daniil
%Y Mueller, Philipp
%Y Borg, Claudia
%Y Šimko, Marián
%S Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F khered-etal-2025-multi
%X Translating Dialectal Arabic (DA) into Modern Standard Arabic (MSA) is a complex task due to the linguistic diversity and informal nature of dialects, particularly in social media texts. To improve translation quality, we propose a Multi-Task Learning (MTL) framework that combines DA-MSA translation as the primary task and dialect identification as an auxiliary task. Additionally, we introduce LahjaTube, a new corpus containing DA transcripts and corresponding MSA and English translations, covering four major Arabic dialects: Egyptian (EGY), Gulf (GLF), Levantine (LEV), and Maghrebi (MGR), collected from YouTube. We evaluate AraT5 and AraBART on the Dial2MSA-Verified dataset under Single-Task Learning (STL) and MTL setups. Our results show that adopting the MTL framework and incorporating LahjaTube into the training data improve the translation performance, leading to a BLEU score improvement of 2.65 points over baseline models.
%U https://aclanthology.org/2025.lowresnlp-1.4/
%P 21-31
Markdown (Informal)
[A Multi-Task Learning Approach to Dialectal Arabic Identification and Translation to Modern Standard Arabic](https://aclanthology.org/2025.lowresnlp-1.4/) (Khered et al., LowResNLP 2025)
ACL