@inproceedings{sakr-torki-2026-knights,
title = "knights-{ST} at {A}ra{S}eg Shared Task 2026: Cross-Family Ensembling with Task-Adaptive Pretraining for {A}rabic Sentence Segmentation",
author = "Sakr, Abdelrahman and
Torki, Marwan",
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.116/",
pages = "938--943",
ISBN = "979-8-89176-497-2",
abstract = "We describe our submission to the AraSeg 2026 shared task on Arabic sentence segmentation (Paragraph-Aware, Closed track). We cast segmentation as binary token-boundary classification and build a system around three ideas: (i) task-adaptive pretraining (TAPT) of encoders on the task{'}s own training text, (ii) regularized fine-tuning with R-Drop and boundary smoothing, and (iii) a hand-designed cross-family ensemble of architecturally diverse Arabic encoders. Our final system reaches a boundary F1 of 94.8 on the blind test set (ranking 3rd of 12 teams, 0.5 points from the top-ranked team). Beyond the score, we report a practical finding backed by a series of blind submissions: on a small development set, a compact diversity-first ensemble generalizes better to unseen data than ensembles selected by exhaustively maximizing development F1, and TAPT helps only under-adapted backbones while hurting a heavily-pretrained one. We also report five techniques that did not help, to save future practitioners the effort. Our code is publicly available at https://github.com/Body123/araseg-2026-knights-st."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakr-torki-2026-knights">
<titleInfo>
<title>knights-ST at AraSeg Shared Task 2026: Cross-Family Ensembling with Task-Adaptive Pretraining for Arabic Sentence Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Sakr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marwan</namePart>
<namePart type="family">Torki</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 our submission to the AraSeg 2026 shared task on Arabic sentence segmentation (Paragraph-Aware, Closed track). We cast segmentation as binary token-boundary classification and build a system around three ideas: (i) task-adaptive pretraining (TAPT) of encoders on the task’s own training text, (ii) regularized fine-tuning with R-Drop and boundary smoothing, and (iii) a hand-designed cross-family ensemble of architecturally diverse Arabic encoders. Our final system reaches a boundary F1 of 94.8 on the blind test set (ranking 3rd of 12 teams, 0.5 points from the top-ranked team). Beyond the score, we report a practical finding backed by a series of blind submissions: on a small development set, a compact diversity-first ensemble generalizes better to unseen data than ensembles selected by exhaustively maximizing development F1, and TAPT helps only under-adapted backbones while hurting a heavily-pretrained one. We also report five techniques that did not help, to save future practitioners the effort. Our code is publicly available at https://github.com/Body123/araseg-2026-knights-st.</abstract>
<identifier type="citekey">sakr-torki-2026-knights</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.116/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>938</start>
<end>943</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T knights-ST at AraSeg Shared Task 2026: Cross-Family Ensembling with Task-Adaptive Pretraining for Arabic Sentence Segmentation
%A Sakr, Abdelrahman
%A Torki, Marwan
%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 sakr-torki-2026-knights
%X We describe our submission to the AraSeg 2026 shared task on Arabic sentence segmentation (Paragraph-Aware, Closed track). We cast segmentation as binary token-boundary classification and build a system around three ideas: (i) task-adaptive pretraining (TAPT) of encoders on the task’s own training text, (ii) regularized fine-tuning with R-Drop and boundary smoothing, and (iii) a hand-designed cross-family ensemble of architecturally diverse Arabic encoders. Our final system reaches a boundary F1 of 94.8 on the blind test set (ranking 3rd of 12 teams, 0.5 points from the top-ranked team). Beyond the score, we report a practical finding backed by a series of blind submissions: on a small development set, a compact diversity-first ensemble generalizes better to unseen data than ensembles selected by exhaustively maximizing development F1, and TAPT helps only under-adapted backbones while hurting a heavily-pretrained one. We also report five techniques that did not help, to save future practitioners the effort. Our code is publicly available at https://github.com/Body123/araseg-2026-knights-st.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.116/
%P 938-943
Markdown (Informal)
[knights-ST at AraSeg Shared Task 2026: Cross-Family Ensembling with Task-Adaptive Pretraining for Arabic Sentence Segmentation](https://aclanthology.org/2026.arabicnlp-sharedtasks.116/) (Sakr & Torki, ArabicNLP 2026)
ACL