@inproceedings{usmani-2026-soloeval,
title = "Soloeval at {BAREC} Shared Task 2026: {QWK}-Aligned Soft-Label Ordinal Classification with Auxiliary Surface Features for {A}rabic Readability Assessment",
author = "Usmani, Turab Hussain",
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.26/",
pages = "225--230",
ISBN = "979-8-89176-497-2",
abstract = "We describe Soloeval{'}s submission to the Sentence-Level Open Track of the BAREC Shared Task 2026 on fine-grained Arabic readability assessment. Rather than treating the 19-level readability scale as a scalar regression target, we fine-tune pretrained Arabic BERT encoders (MARBERTv2 and CAMeLBERT-Mix) with a soft-label cross-entropy objective whose target distribution is a Gaussian centered on the gold level, chosen to more directly reflect the Quadratic Weighted Kappa (QWK) evaluation metric{'}s quadratic distance penalty. We combine this with lightweight auxiliary surface features (sentence length, word count, diacritic density) and K-fold cross-validation. Our best single-model configuration, CAMeLBERT-Mix trained with F=3 folds, achieves a QWK of 80.6 on the BAREC 2026 blind test leaderboard for the Open track. We report our full hyperparameter search, discuss the gap between our dev- and test-set results, and outline what we would try next."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="usmani-2026-soloeval">
<titleInfo>
<title>Soloeval at BAREC Shared Task 2026: QWK-Aligned Soft-Label Ordinal Classification with Auxiliary Surface Features for Arabic Readability Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Turab</namePart>
<namePart type="given">Hussain</namePart>
<namePart type="family">Usmani</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 Soloeval’s submission to the Sentence-Level Open Track of the BAREC Shared Task 2026 on fine-grained Arabic readability assessment. Rather than treating the 19-level readability scale as a scalar regression target, we fine-tune pretrained Arabic BERT encoders (MARBERTv2 and CAMeLBERT-Mix) with a soft-label cross-entropy objective whose target distribution is a Gaussian centered on the gold level, chosen to more directly reflect the Quadratic Weighted Kappa (QWK) evaluation metric’s quadratic distance penalty. We combine this with lightweight auxiliary surface features (sentence length, word count, diacritic density) and K-fold cross-validation. Our best single-model configuration, CAMeLBERT-Mix trained with F=3 folds, achieves a QWK of 80.6 on the BAREC 2026 blind test leaderboard for the Open track. We report our full hyperparameter search, discuss the gap between our dev- and test-set results, and outline what we would try next.</abstract>
<identifier type="citekey">usmani-2026-soloeval</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.26/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>225</start>
<end>230</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Soloeval at BAREC Shared Task 2026: QWK-Aligned Soft-Label Ordinal Classification with Auxiliary Surface Features for Arabic Readability Assessment
%A Usmani, Turab Hussain
%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 usmani-2026-soloeval
%X We describe Soloeval’s submission to the Sentence-Level Open Track of the BAREC Shared Task 2026 on fine-grained Arabic readability assessment. Rather than treating the 19-level readability scale as a scalar regression target, we fine-tune pretrained Arabic BERT encoders (MARBERTv2 and CAMeLBERT-Mix) with a soft-label cross-entropy objective whose target distribution is a Gaussian centered on the gold level, chosen to more directly reflect the Quadratic Weighted Kappa (QWK) evaluation metric’s quadratic distance penalty. We combine this with lightweight auxiliary surface features (sentence length, word count, diacritic density) and K-fold cross-validation. Our best single-model configuration, CAMeLBERT-Mix trained with F=3 folds, achieves a QWK of 80.6 on the BAREC 2026 blind test leaderboard for the Open track. We report our full hyperparameter search, discuss the gap between our dev- and test-set results, and outline what we would try next.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.26/
%P 225-230
Markdown (Informal)
[Soloeval at BAREC Shared Task 2026: QWK-Aligned Soft-Label Ordinal Classification with Auxiliary Surface Features for Arabic Readability Assessment](https://aclanthology.org/2026.arabicnlp-sharedtasks.26/) (Usmani, ArabicNLP 2026)
ACL