@inproceedings{aissaoui-2026-cross,
title = "Cross-Dialectal Transfer for Low-Resource {A}rabic: The {T}unisian {A}rabic Dependency Treebank",
author = "Aissaoui, Amal",
editor = {{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i} and
Dobrovoljc, Kaja},
booktitle = "Proceedings of the Ninth Workshop on {U}niversal {D}ependencies ({UDW} 2026)",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.udw-1.23/",
doi = "10.63317/4vghkox8ptiq",
pages = "258--267",
abstract = "This paper presents a small-scale dependency treebank for Tunisian Arabic (TADT) developed within the Universal Dependencies framework, addressing the scarcity of linguistic resources for the Arabic varieties. The approach employs domain adaptation, leveraging a machine learning model (UDPipe 1.0) trained on Algerian Arabic data to annotate 100 Tunisian Arabic social media comments, followed by manual correction. This pilot study evaluates the feasibility of using machine learning-assisted annotation to scale resource development for spoken Arabic and identifies key challenges in cross-dialectal transfer for improving annotation quality and efficiency. This work contributes to more inclusive and fair representation of Arabic linguistic varieties in academic research and NLP applications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aissaoui-2026-cross">
<titleInfo>
<title>Cross-Dialectal Transfer for Low-Resource Arabic: The Tunisian Arabic Dependency Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Aissaoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Workshop on Universal Dependencies (UDW 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaja</namePart>
<namePart type="family">Dobrovoljc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a small-scale dependency treebank for Tunisian Arabic (TADT) developed within the Universal Dependencies framework, addressing the scarcity of linguistic resources for the Arabic varieties. The approach employs domain adaptation, leveraging a machine learning model (UDPipe 1.0) trained on Algerian Arabic data to annotate 100 Tunisian Arabic social media comments, followed by manual correction. This pilot study evaluates the feasibility of using machine learning-assisted annotation to scale resource development for spoken Arabic and identifies key challenges in cross-dialectal transfer for improving annotation quality and efficiency. This work contributes to more inclusive and fair representation of Arabic linguistic varieties in academic research and NLP applications.</abstract>
<identifier type="citekey">aissaoui-2026-cross</identifier>
<identifier type="doi">10.63317/4vghkox8ptiq</identifier>
<location>
<url>https://aclanthology.org/2026.udw-1.23/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>258</start>
<end>267</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Dialectal Transfer for Low-Resource Arabic: The Tunisian Arabic Dependency Treebank
%A Aissaoui, Amal
%Y Çöltekin, Çağrı
%Y Dobrovoljc, Kaja
%S Proceedings of the Ninth Workshop on Universal Dependencies (UDW 2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F aissaoui-2026-cross
%X This paper presents a small-scale dependency treebank for Tunisian Arabic (TADT) developed within the Universal Dependencies framework, addressing the scarcity of linguistic resources for the Arabic varieties. The approach employs domain adaptation, leveraging a machine learning model (UDPipe 1.0) trained on Algerian Arabic data to annotate 100 Tunisian Arabic social media comments, followed by manual correction. This pilot study evaluates the feasibility of using machine learning-assisted annotation to scale resource development for spoken Arabic and identifies key challenges in cross-dialectal transfer for improving annotation quality and efficiency. This work contributes to more inclusive and fair representation of Arabic linguistic varieties in academic research and NLP applications.
%R 10.63317/4vghkox8ptiq
%U https://aclanthology.org/2026.udw-1.23/
%U https://doi.org/10.63317/4vghkox8ptiq
%P 258-267
Markdown (Informal)
[Cross-Dialectal Transfer for Low-Resource Arabic: The Tunisian Arabic Dependency Treebank](https://aclanthology.org/2026.udw-1.23/) (Aissaoui, UDW 2026)
ACL