<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamad-al-najjar-2026-closed">
    <titleInfo>
        <title>A Closed-Track System for Palestinian Arabic in the AMIYA Shared Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Khaleel</namePart>
        <namePart type="family">Hamad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ahmad</namePart>
        <namePart type="family">Al-Najjar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We describe a closed track system for mod- eling Palestinian Arabic that is developed for the AMIYA shared task using a parameter effi- cient fine-tuning strategy. A 1.5B instruction- tuned language model was adapted with LoRA (Hu et al., 2021), updating only .28% of the model parameters, and trained on an aggre- gated set of conversations between Palestini- ans and resources covering both translation and generation. Model selection was guided by a comparative benchmark that prioritized performance efficiency and its tradeoffs. At the same time the paper focuses on targeting error analysis as well as structured instruction following. These findings illustrate both the viability and shed light on the current limita- tions of efficient adaptation methods for low- resource Arabic dialects.</abstract>
    <identifier type="citekey">hamad-al-najjar-2026-closed</identifier>
    <location>
        <url>https://aclanthology.org/2026.vardial-1.32/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>385</start>
            <end>392</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Closed-Track System for Palestinian Arabic in the AMIYA Shared Task
%A Hamad, Khaleel
%A Al-Najjar, Ahmad
%S Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F hamad-al-najjar-2026-closed
%X We describe a closed track system for mod- eling Palestinian Arabic that is developed for the AMIYA shared task using a parameter effi- cient fine-tuning strategy. A 1.5B instruction- tuned language model was adapted with LoRA (Hu et al., 2021), updating only .28% of the model parameters, and trained on an aggre- gated set of conversations between Palestini- ans and resources covering both translation and generation. Model selection was guided by a comparative benchmark that prioritized performance efficiency and its tradeoffs. At the same time the paper focuses on targeting error analysis as well as structured instruction following. These findings illustrate both the viability and shed light on the current limita- tions of efficient adaptation methods for low- resource Arabic dialects.
%U https://aclanthology.org/2026.vardial-1.32/
%P 385-392

Markdown (Informal)

[A Closed-Track System for Palestinian Arabic in the AMIYA Shared Task](https://aclanthology.org/2026.vardial-1.32/) (Hamad & Al-Najjar, VarDial 2026)

• A Closed-Track System for Palestinian Arabic in the AMIYA Shared Task (Hamad & Al-Najjar, VarDial 2026)

ACL

• Khaleel Hamad and Ahmad Al-Najjar. 2026. A Closed-Track System for Palestinian Arabic in the AMIYA Shared Task. In Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects, pages 385–392, Rabat, Morocco. Association for Computational Linguistics.