@inproceedings{elmadani-etal-2026-barec,
title = "{BAREC}-{TB}: A Dependency Treebank and Parsing Benchmark for {A}rabic Children{'}s Texts",
author = "Elmadani, Khalid N. and
Adel, Mohamed and
AbuOdeh, Muhammed and
Faraj, Reem and
El-Gizuli, Jamila and
Taha, Hanada and
Habash, Nizar",
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.9/",
pages = "115--129",
ISBN = "979-8-89176-473-6",
abstract = "We present BAREC-TB, the first dependency treebank of Arabic children{'}s literature and educational texts. The 156K-word corpus includes texts drawn from eight sources, including curricula, reading materials, children{'}s stories, poems, and songs. The treebank is annotated according to the Columbia Arabic Treebank (CATiB) dependency representation. We compare BAREC-TB with existing Arabic treebanks, including the Penn Arabic Treebank and Camel Treebank, using corpus statistics, dependency-based measures of syntactic complexity, readability and vocabulary-related features. We also establish parsing benchmarks using both a trainable parser and large language models. The corpus will be made publicly available to support Arabic NLP, educational NLP, and language pedagogy research: https://barec.camel-lab.com/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elmadani-etal-2026-barec">
<titleInfo>
<title>BAREC-TB: A Dependency Treebank and Parsing Benchmark for Arabic Children’s Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Elmadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Adel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammed</namePart>
<namePart type="family">AbuOdeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Faraj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamila</namePart>
<namePart type="family">El-Gizuli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanada</namePart>
<namePart type="family">Taha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</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>We present BAREC-TB, the first dependency treebank of Arabic children’s literature and educational texts. The 156K-word corpus includes texts drawn from eight sources, including curricula, reading materials, children’s stories, poems, and songs. The treebank is annotated according to the Columbia Arabic Treebank (CATiB) dependency representation. We compare BAREC-TB with existing Arabic treebanks, including the Penn Arabic Treebank and Camel Treebank, using corpus statistics, dependency-based measures of syntactic complexity, readability and vocabulary-related features. We also establish parsing benchmarks using both a trainable parser and large language models. The corpus will be made publicly available to support Arabic NLP, educational NLP, and language pedagogy research: https://barec.camel-lab.com/.</abstract>
<identifier type="citekey">elmadani-etal-2026-barec</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.9/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>115</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BAREC-TB: A Dependency Treebank and Parsing Benchmark for Arabic Children’s Texts
%A Elmadani, Khalid N.
%A Adel, Mohamed
%A AbuOdeh, Muhammed
%A Faraj, Reem
%A El-Gizuli, Jamila
%A Taha, Hanada
%A Habash, Nizar
%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 elmadani-etal-2026-barec
%X We present BAREC-TB, the first dependency treebank of Arabic children’s literature and educational texts. The 156K-word corpus includes texts drawn from eight sources, including curricula, reading materials, children’s stories, poems, and songs. The treebank is annotated according to the Columbia Arabic Treebank (CATiB) dependency representation. We compare BAREC-TB with existing Arabic treebanks, including the Penn Arabic Treebank and Camel Treebank, using corpus statistics, dependency-based measures of syntactic complexity, readability and vocabulary-related features. We also establish parsing benchmarks using both a trainable parser and large language models. The corpus will be made publicly available to support Arabic NLP, educational NLP, and language pedagogy research: https://barec.camel-lab.com/.
%U https://aclanthology.org/2026.arabicnlp-main.9/
%P 115-129
Markdown (Informal)
[BAREC-TB: A Dependency Treebank and Parsing Benchmark for Arabic Children’s Texts](https://aclanthology.org/2026.arabicnlp-main.9/) (Elmadani et al., ArabicNLP 2026)
ACL