@inproceedings{hamed-etal-2025-lahjawi,
title = "Lahjawi: {A}rabic Cross-Dialect Translator",
author = "Hamed, Mohamed Motasim and
Hreden, Muhammad and
Hennara, Khalil and
Aldallal, Zeina and
Chrouf, Sara and
AlModhayan, Safwan",
editor = "Ezzini, Saad and
Alami, Hamza and
Berrada, Ismail and
Benlahbib, Abdessamad and
El Mahdaouy, Abdelkader and
Lamsiyah, Salima and
Derrouz, Hatim and
Haddad Haddad, Amal and
Jarrar, Mustafa and
El-Haj, Mo and
Mitkov, Ruslan and
Rayson, Paul",
booktitle = "Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wacl-1.2/",
pages = "12--24",
abstract = "In this paper, we explore the rich diversity of Arabic dialects by introducing a suite of pioneering models called Lahjawi. The primary model, Lahjawi-D2D, is the first designed for cross-dialect translation among 15 Arabic dialects. Furthermore, we introduce Lahjawi-D2MSA, a model designed to convert any Arabic dialect into Modern Standard Arabic (MSA). Both models are fine-tuned versions of Kuwain-1.5B an in-house built small language model, tailored for Arabic linguistic characteristics. We provide a detailed overview of Lahjawi`s architecture and training methods, along with a comprehensive evaluation of its performance. The results demonstrate Lahjawi`s success in preserving meaning and style, with BLEU scores of 9.62 for dialect-to-MSA and 9.88 for dialect-to- dialect tasks. Additionally, human evaluation reveals an accuracy score of 58{\%} and a fluency score of 78{\%}, underscoring Lahjawi`s robust handling of diverse dialectal nuances. This research sets a foundation for future advancements in Arabic NLP and cross-dialect communication technologies."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamed-etal-2025-lahjawi">
<titleInfo>
<title>Lahjawi: Arabic Cross-Dialect Translator</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Motasim</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Hreden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Hennara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeina</namePart>
<namePart type="family">Aldallal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Chrouf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Safwan</namePart>
<namePart type="family">AlModhayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamza</namePart>
<namePart type="family">Alami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ismail</namePart>
<namePart type="family">Berrada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdessamad</namePart>
<namePart type="family">Benlahbib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelkader</namePart>
<namePart type="family">El Mahdaouy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salima</namePart>
<namePart type="family">Lamsiyah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatim</namePart>
<namePart type="family">Derrouz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Haddad Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we explore the rich diversity of Arabic dialects by introducing a suite of pioneering models called Lahjawi. The primary model, Lahjawi-D2D, is the first designed for cross-dialect translation among 15 Arabic dialects. Furthermore, we introduce Lahjawi-D2MSA, a model designed to convert any Arabic dialect into Modern Standard Arabic (MSA). Both models are fine-tuned versions of Kuwain-1.5B an in-house built small language model, tailored for Arabic linguistic characteristics. We provide a detailed overview of Lahjawi‘s architecture and training methods, along with a comprehensive evaluation of its performance. The results demonstrate Lahjawi‘s success in preserving meaning and style, with BLEU scores of 9.62 for dialect-to-MSA and 9.88 for dialect-to- dialect tasks. Additionally, human evaluation reveals an accuracy score of 58% and a fluency score of 78%, underscoring Lahjawi‘s robust handling of diverse dialectal nuances. This research sets a foundation for future advancements in Arabic NLP and cross-dialect communication technologies.</abstract>
<identifier type="citekey">hamed-etal-2025-lahjawi</identifier>
<location>
<url>https://aclanthology.org/2025.wacl-1.2/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>12</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lahjawi: Arabic Cross-Dialect Translator
%A Hamed, Mohamed Motasim
%A Hreden, Muhammad
%A Hennara, Khalil
%A Aldallal, Zeina
%A Chrouf, Sara
%A AlModhayan, Safwan
%Y Ezzini, Saad
%Y Alami, Hamza
%Y Berrada, Ismail
%Y Benlahbib, Abdessamad
%Y El Mahdaouy, Abdelkader
%Y Lamsiyah, Salima
%Y Derrouz, Hatim
%Y Haddad Haddad, Amal
%Y Jarrar, Mustafa
%Y El-Haj, Mo
%Y Mitkov, Ruslan
%Y Rayson, Paul
%S Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4)
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F hamed-etal-2025-lahjawi
%X In this paper, we explore the rich diversity of Arabic dialects by introducing a suite of pioneering models called Lahjawi. The primary model, Lahjawi-D2D, is the first designed for cross-dialect translation among 15 Arabic dialects. Furthermore, we introduce Lahjawi-D2MSA, a model designed to convert any Arabic dialect into Modern Standard Arabic (MSA). Both models are fine-tuned versions of Kuwain-1.5B an in-house built small language model, tailored for Arabic linguistic characteristics. We provide a detailed overview of Lahjawi‘s architecture and training methods, along with a comprehensive evaluation of its performance. The results demonstrate Lahjawi‘s success in preserving meaning and style, with BLEU scores of 9.62 for dialect-to-MSA and 9.88 for dialect-to- dialect tasks. Additionally, human evaluation reveals an accuracy score of 58% and a fluency score of 78%, underscoring Lahjawi‘s robust handling of diverse dialectal nuances. This research sets a foundation for future advancements in Arabic NLP and cross-dialect communication technologies.
%U https://aclanthology.org/2025.wacl-1.2/
%P 12-24
Markdown (Informal)
[Lahjawi: Arabic Cross-Dialect Translator](https://aclanthology.org/2025.wacl-1.2/) (Hamed et al., WACL 2025)
ACL
- Mohamed Motasim Hamed, Muhammad Hreden, Khalil Hennara, Zeina Aldallal, Sara Chrouf, and Safwan AlModhayan. 2025. Lahjawi: Arabic Cross-Dialect Translator. In Proceedings of the 4th Workshop on Arabic Corpus Linguistics (WACL-4), pages 12–24, Abu Dhabi, UAE. Association for Computational Linguistics.