@inproceedings{vanetik-etal-2026-daasi,
title = "{DAASI}: {A}rabic Text Simplification Corpus for Israeli Government Documents",
author = "Vanetik, Natalia and
Shareb, Maysa Mosa Abu and
Ismael, Hussein Abo",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.6/",
pages = "65--76",
ISBN = "979-8-89176-473-6",
abstract = "Arabic-speaking citizens in Israel routinely encounter government website documents written in Modern Standard Arabic{~}(MSA), a variety that differs substantially from the Levantine dialect they use daily. This diglossia gap limits access to public services and creates informational inequity, especially for elderly citizens unfamiliar with modern language tools. We address this problem through three contributions. First, we present DAASI (Disglossia-Aware Arabic Simplification for Inclusion): a new parallel corpus of drawn from Israeli National Insurance Institute documents, constructed via GPT-4o draft simplification followed by expert human validation. Second, we conduct a sociolinguistic survey of 50 Arabic-speaking adults in Israel confirming that government documents are harder to comprehend than school-level texts. Third, we benchmark two Arabic transformer models and GPT-4o across multiple fine-tuning strategies and conduct human evaluations to assess simplified text. Our results confirm that existing Arabic NLP benchmarks do not generalize to the Israeli government domain and that DAASI fills a critical resource gap for inclusive Arabic NLP in a diglossic context."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vanetik-etal-2026-daasi">
<titleInfo>
<title>DAASI: Arabic Text Simplification Corpus for Israeli Government Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Vanetik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maysa</namePart>
<namePart type="given">Mosa</namePart>
<namePart type="given">Abu</namePart>
<namePart type="family">Shareb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hussein</namePart>
<namePart type="given">Abo</namePart>
<namePart type="family">Ismael</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>Proceedings of The Fourth Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</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">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</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">Samar</namePart>
<namePart type="family">Magdy</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">Injy</namePart>
<namePart type="family">Hamed</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">Imed</namePart>
<namePart type="family">Zitouni</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">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>Arabic-speaking citizens in Israel routinely encounter government website documents written in Modern Standard Arabic (MSA), a variety that differs substantially from the Levantine dialect they use daily. This diglossia gap limits access to public services and creates informational inequity, especially for elderly citizens unfamiliar with modern language tools. We address this problem through three contributions. First, we present DAASI (Disglossia-Aware Arabic Simplification for Inclusion): a new parallel corpus of drawn from Israeli National Insurance Institute documents, constructed via GPT-4o draft simplification followed by expert human validation. Second, we conduct a sociolinguistic survey of 50 Arabic-speaking adults in Israel confirming that government documents are harder to comprehend than school-level texts. Third, we benchmark two Arabic transformer models and GPT-4o across multiple fine-tuning strategies and conduct human evaluations to assess simplified text. Our results confirm that existing Arabic NLP benchmarks do not generalize to the Israeli government domain and that DAASI fills a critical resource gap for inclusive Arabic NLP in a diglossic context.</abstract>
<identifier type="citekey">vanetik-etal-2026-daasi</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.6/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>65</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DAASI: Arabic Text Simplification Corpus for Israeli Government Documents
%A Vanetik, Natalia
%A Shareb, Maysa Mosa Abu
%A Ismael, Hussein Abo
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F vanetik-etal-2026-daasi
%X Arabic-speaking citizens in Israel routinely encounter government website documents written in Modern Standard Arabic (MSA), a variety that differs substantially from the Levantine dialect they use daily. This diglossia gap limits access to public services and creates informational inequity, especially for elderly citizens unfamiliar with modern language tools. We address this problem through three contributions. First, we present DAASI (Disglossia-Aware Arabic Simplification for Inclusion): a new parallel corpus of drawn from Israeli National Insurance Institute documents, constructed via GPT-4o draft simplification followed by expert human validation. Second, we conduct a sociolinguistic survey of 50 Arabic-speaking adults in Israel confirming that government documents are harder to comprehend than school-level texts. Third, we benchmark two Arabic transformer models and GPT-4o across multiple fine-tuning strategies and conduct human evaluations to assess simplified text. Our results confirm that existing Arabic NLP benchmarks do not generalize to the Israeli government domain and that DAASI fills a critical resource gap for inclusive Arabic NLP in a diglossic context.
%U https://aclanthology.org/2026.arabicnlp-main.6/
%P 65-76
Markdown (Informal)
[DAASI: Arabic Text Simplification Corpus for Israeli Government Documents](https://aclanthology.org/2026.arabicnlp-main.6/) (Vanetik et al., ArabicNLP 2026)
ACL