@inproceedings{dinh-van-2026-hp,
title = "{HP} at {BAREC} Shared Task 2026: Parameter-Efficient Ordinal Regression and Threshold Optimization for {A}rabic Readability.",
author = "{\DJ}inh, Ho{\`a}ng Phong and
V{\u{a}}n, Th{\`i}n {\DJ}ặng",
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.17/",
pages = "160--164",
ISBN = "979-8-89176-497-2",
abstract = "This paper describes the system submitted by team HP for the BAREC Shared Task 2026 on Arabic readability assessment. Driven by the Quadratic Weighted Kappa (QWK) eval- uation metric, which heavily penalizes dis- tant misclassifications, we reframe the 19- level task as an ordinal regression problem rather than standard multi-class classification. Our approach leverages pre-trained language models (AraBERTv02, ARBERT) optimized via Parameter-Efficient Fine-Tuning (LoRA) and trained with a COnsistent RAnk Log- its (CORAL) loss framework incorporating sample-level class weights. To ensure robust generalization, we consolidate the available datasets and implement a 5-fold stratified cross- validation pipeline. Finally, to optimize the QWK metric on the official blind test, we apply an 18-threshold Nelder-Mead optimizer cali- brated exclusively on blended Out-Of-Fold log- its, yielding a blind test QWK of 0.837. Our solution is released in the Github."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dinh-van-2026-hp">
<titleInfo>
<title>HP at BAREC Shared Task 2026: Parameter-Efficient Ordinal Regression and Threshold Optimization for Arabic Readability.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hoàng</namePart>
<namePart type="given">Phong</namePart>
<namePart type="family">Đinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thìn</namePart>
<namePart type="given">Đặng</namePart>
<namePart type="family">Văn</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>This paper describes the system submitted by team HP for the BAREC Shared Task 2026 on Arabic readability assessment. Driven by the Quadratic Weighted Kappa (QWK) eval- uation metric, which heavily penalizes dis- tant misclassifications, we reframe the 19- level task as an ordinal regression problem rather than standard multi-class classification. Our approach leverages pre-trained language models (AraBERTv02, ARBERT) optimized via Parameter-Efficient Fine-Tuning (LoRA) and trained with a COnsistent RAnk Log- its (CORAL) loss framework incorporating sample-level class weights. To ensure robust generalization, we consolidate the available datasets and implement a 5-fold stratified cross- validation pipeline. Finally, to optimize the QWK metric on the official blind test, we apply an 18-threshold Nelder-Mead optimizer cali- brated exclusively on blended Out-Of-Fold log- its, yielding a blind test QWK of 0.837. Our solution is released in the Github.</abstract>
<identifier type="citekey">dinh-van-2026-hp</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.17/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>160</start>
<end>164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HP at BAREC Shared Task 2026: Parameter-Efficient Ordinal Regression and Threshold Optimization for Arabic Readability.
%A Đinh, Hoàng Phong
%A Văn, Thìn Đặng
%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 dinh-van-2026-hp
%X This paper describes the system submitted by team HP for the BAREC Shared Task 2026 on Arabic readability assessment. Driven by the Quadratic Weighted Kappa (QWK) eval- uation metric, which heavily penalizes dis- tant misclassifications, we reframe the 19- level task as an ordinal regression problem rather than standard multi-class classification. Our approach leverages pre-trained language models (AraBERTv02, ARBERT) optimized via Parameter-Efficient Fine-Tuning (LoRA) and trained with a COnsistent RAnk Log- its (CORAL) loss framework incorporating sample-level class weights. To ensure robust generalization, we consolidate the available datasets and implement a 5-fold stratified cross- validation pipeline. Finally, to optimize the QWK metric on the official blind test, we apply an 18-threshold Nelder-Mead optimizer cali- brated exclusively on blended Out-Of-Fold log- its, yielding a blind test QWK of 0.837. Our solution is released in the Github.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.17/
%P 160-164
Markdown (Informal)
[HP at BAREC Shared Task 2026: Parameter-Efficient Ordinal Regression and Threshold Optimization for Arabic Readability.](https://aclanthology.org/2026.arabicnlp-sharedtasks.17/) (Đinh & Văn, ArabicNLP 2026)
ACL