@inproceedings{toughrai-etal-2025-modeling,
title = "Modeling {N}orth {A}frican Dialects from Standard Languages",
author = {Toughrai, Yassine and
Sma{\"i}li, Kamel and
Langlois, David},
editor = "Darwish, Kareem and
Ali, Ahmed and
Abu Farha, Ibrahim and
Touileb, Samia and
Zitouni, Imed and
Abdelali, Ahmed and
Al-Ghamdi, Sharefah and
Alkhereyf, Sakhar and
Zaghouani, Wajdi and
Khalifa, Salam and
AlKhamissi, Badr and
Almatham, Rawan and
Hamed, Injy and
Alyafeai, Zaid and
Alowisheq, Areeb and
Inoue, Go and
Mrini, Khalil and
Alshammari, Waad",
booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.arabicnlp-main.30/",
pages = "375--383",
ISBN = "979-8-89176-352-4",
abstract = "Processing North African Arabic dialects presents significant challenges due to high lexical variability, frequent code-switching with French, and the use of both Arabic and Latin scripts. We address this with a phonemebased normalization strategy that maps Arabic and French text into a simplified representation (Arabic rendered in Latin script), reflecting native reading patterns. Using this method, we pretrain BERTbased models on normalized Modern Standard Arabic and French only and evaluate them on Named Entity Recognition (NER) and text classification. Experiments show that normalized standard-language corpora yield competitive performance on North African dialect tasks; in zero-shot NER, Ar{\_}20k surpasses dialectpretrained baselines. Normalization improves vocabulary alignment, indicating that normalized standard corpora can suffice for developing dialect-supportive"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toughrai-etal-2025-modeling">
<titleInfo>
<title>Modeling North African Dialects from Standard Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yassine</namePart>
<namePart type="family">Toughrai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kamel</namePart>
<namePart type="family">Smaïli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Langlois</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Third Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</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">Samia</namePart>
<namePart type="family">Touileb</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">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharefah</namePart>
<namePart type="family">Al-Ghamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</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">Salam</namePart>
<namePart type="family">Khalifa</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">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Areeb</namePart>
<namePart type="family">Alowisheq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Go</namePart>
<namePart type="family">Inoue</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">Waad</namePart>
<namePart type="family">Alshammari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-352-4</identifier>
</relatedItem>
<abstract>Processing North African Arabic dialects presents significant challenges due to high lexical variability, frequent code-switching with French, and the use of both Arabic and Latin scripts. We address this with a phonemebased normalization strategy that maps Arabic and French text into a simplified representation (Arabic rendered in Latin script), reflecting native reading patterns. Using this method, we pretrain BERTbased models on normalized Modern Standard Arabic and French only and evaluate them on Named Entity Recognition (NER) and text classification. Experiments show that normalized standard-language corpora yield competitive performance on North African dialect tasks; in zero-shot NER, Ar_20k surpasses dialectpretrained baselines. Normalization improves vocabulary alignment, indicating that normalized standard corpora can suffice for developing dialect-supportive</abstract>
<identifier type="citekey">toughrai-etal-2025-modeling</identifier>
<location>
<url>https://aclanthology.org/2025.arabicnlp-main.30/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>375</start>
<end>383</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling North African Dialects from Standard Languages
%A Toughrai, Yassine
%A Smaïli, Kamel
%A Langlois, David
%Y Darwish, Kareem
%Y Ali, Ahmed
%Y Abu Farha, Ibrahim
%Y Touileb, Samia
%Y Zitouni, Imed
%Y Abdelali, Ahmed
%Y Al-Ghamdi, Sharefah
%Y Alkhereyf, Sakhar
%Y Zaghouani, Wajdi
%Y Khalifa, Salam
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Hamed, Injy
%Y Alyafeai, Zaid
%Y Alowisheq, Areeb
%Y Inoue, Go
%Y Mrini, Khalil
%Y Alshammari, Waad
%S Proceedings of The Third Arabic Natural Language Processing Conference
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-352-4
%F toughrai-etal-2025-modeling
%X Processing North African Arabic dialects presents significant challenges due to high lexical variability, frequent code-switching with French, and the use of both Arabic and Latin scripts. We address this with a phonemebased normalization strategy that maps Arabic and French text into a simplified representation (Arabic rendered in Latin script), reflecting native reading patterns. Using this method, we pretrain BERTbased models on normalized Modern Standard Arabic and French only and evaluate them on Named Entity Recognition (NER) and text classification. Experiments show that normalized standard-language corpora yield competitive performance on North African dialect tasks; in zero-shot NER, Ar_20k surpasses dialectpretrained baselines. Normalization improves vocabulary alignment, indicating that normalized standard corpora can suffice for developing dialect-supportive
%U https://aclanthology.org/2025.arabicnlp-main.30/
%P 375-383
Markdown (Informal)
[Modeling North African Dialects from Standard Languages](https://aclanthology.org/2025.arabicnlp-main.30/) (Toughrai et al., ArabicNLP 2025)
ACL