@inproceedings{emam-etal-2026-ensar,
title = "{ENSAR} at {A}ra{S}eg Shared Task 2026: An Ensemble of Encoders With Agentic Error Refinement",
author = "Emam, Noor and
Saqr, Omar Mokhtar Gaber and
Gaafar, Mostafa and
Elaswad, Ali",
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.117/",
pages = "944--955",
ISBN = "979-8-89176-497-2",
abstract = "We describe ENSAR, our submission to the AraSeg 2026 shared task on Arabic sentence segmentation, where a system must decide, for every word in a document, whether a sentence ends there. The four tracks strip punctuation, paragraph breaks, both, or neither. We start from an ensemble of five fine-tuned encoders decoded with a length-aware semi-Markov program. It is strong, but most of its mistakes are places where all five models are wrong and all five assign high confidence, so averaging them or moving a threshold changes nothing. ENSAR adds a reasoning stage on top. Two LLM juries, each holding a written policy learned from its own graded errors on the training split, debate every document and apply only the edits both endorse. Our system ranked first on three of the four tracks in both the closed and open settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="emam-etal-2026-ensar">
<titleInfo>
<title>ENSAR at AraSeg Shared Task 2026: An Ensemble of Encoders With Agentic Error Refinement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noor</namePart>
<namePart type="family">Emam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="given">Mokhtar</namePart>
<namePart type="given">Gaber</namePart>
<namePart type="family">Saqr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mostafa</namePart>
<namePart type="family">Gaafar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Elaswad</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 ENSAR, our submission to the AraSeg 2026 shared task on Arabic sentence segmentation, where a system must decide, for every word in a document, whether a sentence ends there. The four tracks strip punctuation, paragraph breaks, both, or neither. We start from an ensemble of five fine-tuned encoders decoded with a length-aware semi-Markov program. It is strong, but most of its mistakes are places where all five models are wrong and all five assign high confidence, so averaging them or moving a threshold changes nothing. ENSAR adds a reasoning stage on top. Two LLM juries, each holding a written policy learned from its own graded errors on the training split, debate every document and apply only the edits both endorse. Our system ranked first on three of the four tracks in both the closed and open settings.</abstract>
<identifier type="citekey">emam-etal-2026-ensar</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.117/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>944</start>
<end>955</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ENSAR at AraSeg Shared Task 2026: An Ensemble of Encoders With Agentic Error Refinement
%A Emam, Noor
%A Saqr, Omar Mokhtar Gaber
%A Gaafar, Mostafa
%A Elaswad, Ali
%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 emam-etal-2026-ensar
%X We describe ENSAR, our submission to the AraSeg 2026 shared task on Arabic sentence segmentation, where a system must decide, for every word in a document, whether a sentence ends there. The four tracks strip punctuation, paragraph breaks, both, or neither. We start from an ensemble of five fine-tuned encoders decoded with a length-aware semi-Markov program. It is strong, but most of its mistakes are places where all five models are wrong and all five assign high confidence, so averaging them or moving a threshold changes nothing. ENSAR adds a reasoning stage on top. Two LLM juries, each holding a written policy learned from its own graded errors on the training split, debate every document and apply only the edits both endorse. Our system ranked first on three of the four tracks in both the closed and open settings.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.117/
%P 944-955
Markdown (Informal)
[ENSAR at AraSeg Shared Task 2026: An Ensemble of Encoders With Agentic Error Refinement](https://aclanthology.org/2026.arabicnlp-sharedtasks.117/) (Emam et al., ArabicNLP 2026)
ACL