@inproceedings{almajai-2026-itgan-araseg,
title = "Itgan at {A}ra{S}eg Shared Task 2026: Diversify, Don{'}t Curate {--} Learned Ensemble Combination for {A}rabic Sentence Segmentation",
author = "Almajai, Ibrahim",
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.122/",
pages = "995--1003",
ISBN = "979-8-89176-497-2",
abstract = "We describe our submissions to the four subtasks of the AraSeg 2026 shared task in both tracks. Our components are conventional word-level boundary taggers, and our contribution is a measurement of what combining them is worth. Averaging 21 members gains +0.89 F1 over the best single model, and replacing the uniform probability average with a learned logistic combiner adds a further +0.23 (+1.12 in total), reaching significance only on the two subtasks that lack punctuation. Both are smaller than the encoder swap (+1.82). What the combiner buys is freedom from curation. Added to the base encoder, each of six different pretrained encoders helps under the combiner (+0.12 to +0.72, mean +0.34), whereas under averaging three of the six are harmful, by as much as 0.62. Another seed of an existing encoder is worth nothing under either rule; members should therefore be diversified rather than curated, provided the weights are learned. We also report three null results for inference-time structure, including a semi-Markov CRF whose failure we trace to a length prior that is uninformative at corpus level. Our closed-track systems placed fifth and seventh where ranked. In the open track, pretraining on 3.2M tokens of silver boundaries from Arabic Wikipedia before fine-tuning on the gold training split is worth +0.58 F1, and two of the closed-track findings reproduce on that external data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almajai-2026-itgan-araseg">
<titleInfo>
<title>Itgan at AraSeg Shared Task 2026: Diversify, Don’t Curate – Learned Ensemble Combination for Arabic Sentence Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Almajai</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 submissions to the four subtasks of the AraSeg 2026 shared task in both tracks. Our components are conventional word-level boundary taggers, and our contribution is a measurement of what combining them is worth. Averaging 21 members gains +0.89 F1 over the best single model, and replacing the uniform probability average with a learned logistic combiner adds a further +0.23 (+1.12 in total), reaching significance only on the two subtasks that lack punctuation. Both are smaller than the encoder swap (+1.82). What the combiner buys is freedom from curation. Added to the base encoder, each of six different pretrained encoders helps under the combiner (+0.12 to +0.72, mean +0.34), whereas under averaging three of the six are harmful, by as much as 0.62. Another seed of an existing encoder is worth nothing under either rule; members should therefore be diversified rather than curated, provided the weights are learned. We also report three null results for inference-time structure, including a semi-Markov CRF whose failure we trace to a length prior that is uninformative at corpus level. Our closed-track systems placed fifth and seventh where ranked. In the open track, pretraining on 3.2M tokens of silver boundaries from Arabic Wikipedia before fine-tuning on the gold training split is worth +0.58 F1, and two of the closed-track findings reproduce on that external data.</abstract>
<identifier type="citekey">almajai-2026-itgan-araseg</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.122/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>995</start>
<end>1003</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Itgan at AraSeg Shared Task 2026: Diversify, Don’t Curate – Learned Ensemble Combination for Arabic Sentence Segmentation
%A Almajai, Ibrahim
%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 almajai-2026-itgan-araseg
%X We describe our submissions to the four subtasks of the AraSeg 2026 shared task in both tracks. Our components are conventional word-level boundary taggers, and our contribution is a measurement of what combining them is worth. Averaging 21 members gains +0.89 F1 over the best single model, and replacing the uniform probability average with a learned logistic combiner adds a further +0.23 (+1.12 in total), reaching significance only on the two subtasks that lack punctuation. Both are smaller than the encoder swap (+1.82). What the combiner buys is freedom from curation. Added to the base encoder, each of six different pretrained encoders helps under the combiner (+0.12 to +0.72, mean +0.34), whereas under averaging three of the six are harmful, by as much as 0.62. Another seed of an existing encoder is worth nothing under either rule; members should therefore be diversified rather than curated, provided the weights are learned. We also report three null results for inference-time structure, including a semi-Markov CRF whose failure we trace to a length prior that is uninformative at corpus level. Our closed-track systems placed fifth and seventh where ranked. In the open track, pretraining on 3.2M tokens of silver boundaries from Arabic Wikipedia before fine-tuning on the gold training split is worth +0.58 F1, and two of the closed-track findings reproduce on that external data.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.122/
%P 995-1003
Markdown (Informal)
[Itgan at AraSeg Shared Task 2026: Diversify, Don’t Curate – Learned Ensemble Combination for Arabic Sentence Segmentation](https://aclanthology.org/2026.arabicnlp-sharedtasks.122/) (Almajai, ArabicNLP 2026)
ACL