@inproceedings{zaher-2026-zhr,
title = "{ZHR} at {BAREC} Shared Task 2026: Ordinal-Objective Ensembles with Threshold Calibration and Silver-Label Pretraining for {A}rabic Readability Assessment",
author = "Zaher, Mahmoud",
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: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.24/",
pages = "209--218",
ISBN = "979-8-89176-497-2",
abstract = "We describe the ZHR systems for the two sentence-level tracks of the BAREC 2026 Shared Task on Arabic readability assessment: Strict, where training is restricted to the BAREC training split, and Open, which allows any public data. Each sentence receives one of 19 ordinal levels, and systems are ranked by quadratic weighted kappa (QWK). Both tracks use one recipe. Arabic encoders are fine-tuned under five ordinal objectives and averaged with weights from greedy selection, and the averaged score is discretized by 18 thresholds fitted to maximize QWK; every fitted quantity uses the development split. The official Strict system, an ensemble of ten train-split models, scores 85.0 QWK on the blind set. The official Open system adds pretraining on the silver-labeled BAREC-10M corpus and restricts selection to members whose early stopping never touched the calibration split; it scores 85.2. Both clear the official baseline (82.5) by 2.5 and 2.7 QWK while trailing it in exact accuracy, a trade-off that comes from the metric itself and that we measure directly. Negative results are part of the record: a catalog of 19 changes that did not help, each measured under a held-out protocol."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaher-2026-zhr">
<titleInfo>
<title>ZHR at BAREC Shared Task 2026: Ordinal-Objective Ensembles with Threshold Calibration and Silver-Label Pretraining for Arabic Readability Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Zaher</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: Shared Tasks</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">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>We describe the ZHR systems for the two sentence-level tracks of the BAREC 2026 Shared Task on Arabic readability assessment: Strict, where training is restricted to the BAREC training split, and Open, which allows any public data. Each sentence receives one of 19 ordinal levels, and systems are ranked by quadratic weighted kappa (QWK). Both tracks use one recipe. Arabic encoders are fine-tuned under five ordinal objectives and averaged with weights from greedy selection, and the averaged score is discretized by 18 thresholds fitted to maximize QWK; every fitted quantity uses the development split. The official Strict system, an ensemble of ten train-split models, scores 85.0 QWK on the blind set. The official Open system adds pretraining on the silver-labeled BAREC-10M corpus and restricts selection to members whose early stopping never touched the calibration split; it scores 85.2. Both clear the official baseline (82.5) by 2.5 and 2.7 QWK while trailing it in exact accuracy, a trade-off that comes from the metric itself and that we measure directly. Negative results are part of the record: a catalog of 19 changes that did not help, each measured under a held-out protocol.</abstract>
<identifier type="citekey">zaher-2026-zhr</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.24/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>209</start>
<end>218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ZHR at BAREC Shared Task 2026: Ordinal-Objective Ensembles with Threshold Calibration and Silver-Label Pretraining for Arabic Readability Assessment
%A Zaher, Mahmoud
%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: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F zaher-2026-zhr
%X We describe the ZHR systems for the two sentence-level tracks of the BAREC 2026 Shared Task on Arabic readability assessment: Strict, where training is restricted to the BAREC training split, and Open, which allows any public data. Each sentence receives one of 19 ordinal levels, and systems are ranked by quadratic weighted kappa (QWK). Both tracks use one recipe. Arabic encoders are fine-tuned under five ordinal objectives and averaged with weights from greedy selection, and the averaged score is discretized by 18 thresholds fitted to maximize QWK; every fitted quantity uses the development split. The official Strict system, an ensemble of ten train-split models, scores 85.0 QWK on the blind set. The official Open system adds pretraining on the silver-labeled BAREC-10M corpus and restricts selection to members whose early stopping never touched the calibration split; it scores 85.2. Both clear the official baseline (82.5) by 2.5 and 2.7 QWK while trailing it in exact accuracy, a trade-off that comes from the metric itself and that we measure directly. Negative results are part of the record: a catalog of 19 changes that did not help, each measured under a held-out protocol.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.24/
%P 209-218
Markdown (Informal)
[ZHR at BAREC Shared Task 2026: Ordinal-Objective Ensembles with Threshold Calibration and Silver-Label Pretraining for Arabic Readability Assessment](https://aclanthology.org/2026.arabicnlp-sharedtasks.24/) (Zaher, ArabicNLP 2026)
ACL