@inproceedings{chhaytle-etal-2026-knowledge,
title = "Knowledge Graphs and Distributional Readability of {A}rabic Documents",
author = "Chhaytle, Mohamad and
Hamoud, Hadi and
Choker, Sally and
Abou Chakra, Chadi and
Ballout, Mohamad and
Zaraket, Fadi",
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.35/",
pages = "508--521",
ISBN = "979-8-89176-473-6",
abstract = "This paper addresses automatic readability assessment of Arabic documents. It compares classical readability formulae, fine-tuned Arabic encoders, zero-shot large language models and a Co-occurrence Graphs for Arabic Readability (CoGAR). CoGAR, interpretable and LLM-free, represents a document as a co-occurrence network over content lemmas and use topology features such as density, clustering, path length and degree entropy to predict readability. Evaluated on the BAREC corpus over five ordinal levels, the method reaches a quadratic weighted kappa (QWK) of 0.756, on par with a sparse 35B-parameter LLM and well above the surface formulas Flesch and OSMAN.\par An ablation shows that the signal lies in the graph{'}s shape rather than size, and that alternative graphs based on relations between named-entity carry almost no readability difficulty signal. We further distill a frontier LLM (Gemini) into a small Arabic encoder (NeoAraBERT) by silver labelling 30k chunks, reaching 0.714 QWK. We show that stacking an LLM with CoGAR improves on the LLM alone, reaching QWK 0.839 with GPT-4.1 and 0.852 with the open-weight Qwen-35B, our best result. The two signals are complementary and the gain does not depend on a proprietary model. Finally, we analyze how eight methods including CoGAR distribute reading levels across seven Arabic text sources ranging from children books to expert research manuscripts showing how the methods align with intuitive difficulty."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chhaytle-etal-2026-knowledge">
<titleInfo>
<title>Knowledge Graphs and Distributional Readability of Arabic Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamad</namePart>
<namePart type="family">Chhaytle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hadi</namePart>
<namePart type="family">Hamoud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sally</namePart>
<namePart type="family">Choker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chadi</namePart>
<namePart type="family">Abou Chakra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamad</namePart>
<namePart type="family">Ballout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fadi</namePart>
<namePart type="family">Zaraket</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>This paper addresses automatic readability assessment of Arabic documents. It compares classical readability formulae, fine-tuned Arabic encoders, zero-shot large language models and a Co-occurrence Graphs for Arabic Readability (CoGAR). CoGAR, interpretable and LLM-free, represents a document as a co-occurrence network over content lemmas and use topology features such as density, clustering, path length and degree entropy to predict readability. Evaluated on the BAREC corpus over five ordinal levels, the method reaches a quadratic weighted kappa (QWK) of 0.756, on par with a sparse 35B-parameter LLM and well above the surface formulas Flesch and OSMAN.\par An ablation shows that the signal lies in the graph’s shape rather than size, and that alternative graphs based on relations between named-entity carry almost no readability difficulty signal. We further distill a frontier LLM (Gemini) into a small Arabic encoder (NeoAraBERT) by silver labelling 30k chunks, reaching 0.714 QWK. We show that stacking an LLM with CoGAR improves on the LLM alone, reaching QWK 0.839 with GPT-4.1 and 0.852 with the open-weight Qwen-35B, our best result. The two signals are complementary and the gain does not depend on a proprietary model. Finally, we analyze how eight methods including CoGAR distribute reading levels across seven Arabic text sources ranging from children books to expert research manuscripts showing how the methods align with intuitive difficulty.</abstract>
<identifier type="citekey">chhaytle-etal-2026-knowledge</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.35/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>508</start>
<end>521</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Graphs and Distributional Readability of Arabic Documents
%A Chhaytle, Mohamad
%A Hamoud, Hadi
%A Choker, Sally
%A Abou Chakra, Chadi
%A Ballout, Mohamad
%A Zaraket, Fadi
%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 chhaytle-etal-2026-knowledge
%X This paper addresses automatic readability assessment of Arabic documents. It compares classical readability formulae, fine-tuned Arabic encoders, zero-shot large language models and a Co-occurrence Graphs for Arabic Readability (CoGAR). CoGAR, interpretable and LLM-free, represents a document as a co-occurrence network over content lemmas and use topology features such as density, clustering, path length and degree entropy to predict readability. Evaluated on the BAREC corpus over five ordinal levels, the method reaches a quadratic weighted kappa (QWK) of 0.756, on par with a sparse 35B-parameter LLM and well above the surface formulas Flesch and OSMAN.\par An ablation shows that the signal lies in the graph’s shape rather than size, and that alternative graphs based on relations between named-entity carry almost no readability difficulty signal. We further distill a frontier LLM (Gemini) into a small Arabic encoder (NeoAraBERT) by silver labelling 30k chunks, reaching 0.714 QWK. We show that stacking an LLM with CoGAR improves on the LLM alone, reaching QWK 0.839 with GPT-4.1 and 0.852 with the open-weight Qwen-35B, our best result. The two signals are complementary and the gain does not depend on a proprietary model. Finally, we analyze how eight methods including CoGAR distribute reading levels across seven Arabic text sources ranging from children books to expert research manuscripts showing how the methods align with intuitive difficulty.
%U https://aclanthology.org/2026.arabicnlp-main.35/
%P 508-521
Markdown (Informal)
[Knowledge Graphs and Distributional Readability of Arabic Documents](https://aclanthology.org/2026.arabicnlp-main.35/) (Chhaytle et al., ArabicNLP 2026)
ACL