@inproceedings{keleg-etal-2026-romanized,
title = "{R}omanized {A}rabic Across Dialects: Views, Usage Patterns, and Linguistic Variation",
author = "Keleg, Amr and
Abdallah, Ahmed Amine Ben and
Yassine, Taha and
Helwe, Chadi and
Guellil, Imane and
Ousidhoum, Nedjma",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.900/",
pages = "19050--19079",
ISBN = "979-8-89176-462-0",
abstract = "Arabizi refers to Arabic written in Latin script. Although previous studies have shown that the prevalence and usage of Arabizi vary by factors such as region and age group, most NLP research on Arabic texts treats it as a temporary phenomenon resulting from limited technological support for the Arabic script. In this work, we engage with Arabic speakers to collect insights on their perceptions and usage of Arabizi. We further examine writing norms among speakers of different dialects, focusing on Algerian, Egyptian, Lebanese, Moroccan, and Tunisian Arabic. To this end, we release two resources. First, we perform a character-level alignment of Arabic words to study inter- and intra-dialectal variation across these five dialects, based on words transliterated by the surveyed participants (VARabiziLex), finding systematic intradialectal regularity and inter-dialectal variation. Second, to study Arabic speakers' ability to identify this stylistic variation at the sentence-level, we build VARabiziCues, a manually curated parallel corpus of sentences written in Arabic script alongside multiple Arabizi transliterations, collected from speakers of the same five dialects. Our study presents the largest human-centered, cross-dialectal study of Arabizi{'}s perceptions and practices to date."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keleg-etal-2026-romanized">
<titleInfo>
<title>Romanized Arabic Across Dialects: Views, Usage Patterns, and Linguistic Variation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Amine</namePart>
<namePart type="given">Ben</namePart>
<namePart type="family">Abdallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taha</namePart>
<namePart type="family">Yassine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chadi</namePart>
<namePart type="family">Helwe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imane</namePart>
<namePart type="family">Guellil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nedjma</namePart>
<namePart type="family">Ousidhoum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Arabizi refers to Arabic written in Latin script. Although previous studies have shown that the prevalence and usage of Arabizi vary by factors such as region and age group, most NLP research on Arabic texts treats it as a temporary phenomenon resulting from limited technological support for the Arabic script. In this work, we engage with Arabic speakers to collect insights on their perceptions and usage of Arabizi. We further examine writing norms among speakers of different dialects, focusing on Algerian, Egyptian, Lebanese, Moroccan, and Tunisian Arabic. To this end, we release two resources. First, we perform a character-level alignment of Arabic words to study inter- and intra-dialectal variation across these five dialects, based on words transliterated by the surveyed participants (VARabiziLex), finding systematic intradialectal regularity and inter-dialectal variation. Second, to study Arabic speakers’ ability to identify this stylistic variation at the sentence-level, we build VARabiziCues, a manually curated parallel corpus of sentences written in Arabic script alongside multiple Arabizi transliterations, collected from speakers of the same five dialects. Our study presents the largest human-centered, cross-dialectal study of Arabizi’s perceptions and practices to date.</abstract>
<identifier type="citekey">keleg-etal-2026-romanized</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.900/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>19050</start>
<end>19079</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Romanized Arabic Across Dialects: Views, Usage Patterns, and Linguistic Variation
%A Keleg, Amr
%A Abdallah, Ahmed Amine Ben
%A Yassine, Taha
%A Helwe, Chadi
%A Guellil, Imane
%A Ousidhoum, Nedjma
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F keleg-etal-2026-romanized
%X Arabizi refers to Arabic written in Latin script. Although previous studies have shown that the prevalence and usage of Arabizi vary by factors such as region and age group, most NLP research on Arabic texts treats it as a temporary phenomenon resulting from limited technological support for the Arabic script. In this work, we engage with Arabic speakers to collect insights on their perceptions and usage of Arabizi. We further examine writing norms among speakers of different dialects, focusing on Algerian, Egyptian, Lebanese, Moroccan, and Tunisian Arabic. To this end, we release two resources. First, we perform a character-level alignment of Arabic words to study inter- and intra-dialectal variation across these five dialects, based on words transliterated by the surveyed participants (VARabiziLex), finding systematic intradialectal regularity and inter-dialectal variation. Second, to study Arabic speakers’ ability to identify this stylistic variation at the sentence-level, we build VARabiziCues, a manually curated parallel corpus of sentences written in Arabic script alongside multiple Arabizi transliterations, collected from speakers of the same five dialects. Our study presents the largest human-centered, cross-dialectal study of Arabizi’s perceptions and practices to date.
%U https://aclanthology.org/2026.findings-emnlp.900/
%P 19050-19079
Markdown (Informal)
[Romanized Arabic Across Dialects: Views, Usage Patterns, and Linguistic Variation](https://aclanthology.org/2026.findings-emnlp.900/) (Keleg et al., Findings 2026)
ACL
- Amr Keleg, Ahmed Amine Ben Abdallah, Taha Yassine, Chadi Helwe, Imane Guellil, and Nedjma Ousidhoum. 2026. Romanized Arabic Across Dialects: Views, Usage Patterns, and Linguistic Variation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 19050–19079, Budapest, Hungary. Association for Computational Linguistics.