@inproceedings{khered-etal-2025-dial2msa,
title = "{D}ial2{MSA}-Verified: A Multi-Dialect {A}rabic Social Media Dataset for Neural Machine Translation to {M}odern {S}tandard {A}rabic",
author = "Khered, Abdullah Salem and
Benkhedda, Youcef and
Batista-Navarro, Riza",
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-1.6/",
pages = "50--62",
abstract = "Social media has become an essential focus for Natural Language Processing (NLP) research due to its widespread use and unique linguistic characteristics. Normalising social media content, especially for morphologically rich languages like Arabic, remains a complex task due to limited parallel corpora. Arabic encompasses Modern Standard Arabic (MSA) and various regional dialects, collectively termed Dialectal Arabic (DA), which complicates NLP efforts due to their informal nature and variability. This paper presents Dial2MSA-Verified, an extension of the Dial2MSA dataset that includes verified translations for Gulf, Egyptian, Levantine, and Maghrebi dialects. We evaluate the performance of Seq2Seq models on this dataset, highlighting the effectiveness of state-of-the-art models in translating local Arabic dialects. We also provide insights through error analysis and outline future directions for enhancing Seq2Seq models and dataset development. The Dial2MSA-Verified dataset is publicly available to support further research."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khered-etal-2025-dial2msa">
<titleInfo>
<title>Dial2MSA-Verified: A Multi-Dialect Arabic Social Media Dataset for Neural Machine Translation to Modern Standard Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="given">Salem</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>2025-01</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>Social media has become an essential focus for Natural Language Processing (NLP) research due to its widespread use and unique linguistic characteristics. Normalising social media content, especially for morphologically rich languages like Arabic, remains a complex task due to limited parallel corpora. Arabic encompasses Modern Standard Arabic (MSA) and various regional dialects, collectively termed Dialectal Arabic (DA), which complicates NLP efforts due to their informal nature and variability. This paper presents Dial2MSA-Verified, an extension of the Dial2MSA dataset that includes verified translations for Gulf, Egyptian, Levantine, and Maghrebi dialects. We evaluate the performance of Seq2Seq models on this dataset, highlighting the effectiveness of state-of-the-art models in translating local Arabic dialects. We also provide insights through error analysis and outline future directions for enhancing Seq2Seq models and dataset development. The Dial2MSA-Verified dataset is publicly available to support further research.</abstract>
<identifier type="citekey">khered-etal-2025-dial2msa</identifier>
<location>
<url>https://aclanthology.org/2025.wacl-1.6/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>50</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dial2MSA-Verified: A Multi-Dialect Arabic Social Media Dataset for Neural Machine Translation to Modern Standard Arabic
%A Khered, Abdullah Salem
%A Benkhedda, Youcef
%A Batista-Navarro, Riza
%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 khered-etal-2025-dial2msa
%X Social media has become an essential focus for Natural Language Processing (NLP) research due to its widespread use and unique linguistic characteristics. Normalising social media content, especially for morphologically rich languages like Arabic, remains a complex task due to limited parallel corpora. Arabic encompasses Modern Standard Arabic (MSA) and various regional dialects, collectively termed Dialectal Arabic (DA), which complicates NLP efforts due to their informal nature and variability. This paper presents Dial2MSA-Verified, an extension of the Dial2MSA dataset that includes verified translations for Gulf, Egyptian, Levantine, and Maghrebi dialects. We evaluate the performance of Seq2Seq models on this dataset, highlighting the effectiveness of state-of-the-art models in translating local Arabic dialects. We also provide insights through error analysis and outline future directions for enhancing Seq2Seq models and dataset development. The Dial2MSA-Verified dataset is publicly available to support further research.
%U https://aclanthology.org/2025.wacl-1.6/
%P 50-62
Markdown (Informal)
[Dial2MSA-Verified: A Multi-Dialect Arabic Social Media Dataset for Neural Machine Translation to Modern Standard Arabic](https://aclanthology.org/2025.wacl-1.6/) (Khered et al., WACL 2025)
ACL