@inproceedings{duridi-etal-2026-ptuk,
title = "{PTUK}-{NLP} at {K}nowledge{G}raph{E}val 2026: Cross-Domain Nested {A}rabic {NER} with {A}r{BERT} and Targeted Data Augmentation",
author = "Duridi, Tasneem and
Salih, Islam HJ and
Jawabreh, Mariam and
Jaber, Areej and
Jaber, Elaa",
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.151/",
pages = "1205--1211",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents the PTUK-NLP submission to KnowledgeGraphEval 2026 Subtask 1 (AdaptNER), evaluating cross-domain and cross-dialect nested Arabic Named Entity Recognition (NER). Models trained on Wojood are evaluated in a zero-shot setting on Konooz, spanning ten unseen domains and sixteen Arabic dialects. Our system fine-tunes ArBERT with targeted augmentation for rare entity types and lightweight inference-time post-processing, using Konooz strictly for evaluation and never for training or adaptation. The submitted system achieves 91.07{\%} micro-F1 and 83.11{\%} macro-F1 on Wojood, and 71.84{\%} precision, 66.59{\%} recall, 69.11{\%} micro-F1, and 60.70{\%} macro-F1 on the official Konooz blind test, ranking fourth on the final leaderboard and achieving a micro-F1 score 6.11 points above the organizers' baseline. A post-submission ensemble of ArBERT and AraBERTv2 does not improve over the best single model. Overall, targeted data-centric modifications provide useful gains for rare entity types, while a standard MSA-pretrained encoder remains competitive under substantial domain and dialect shift."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duridi-etal-2026-ptuk">
<titleInfo>
<title>PTUK-NLP at KnowledgeGraphEval 2026: Cross-Domain Nested Arabic NER with ArBERT and Targeted Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tasneem</namePart>
<namePart type="family">Duridi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Islam</namePart>
<namePart type="given">HJ</namePart>
<namePart type="family">Salih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="family">Jawabreh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Areej</namePart>
<namePart type="family">Jaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elaa</namePart>
<namePart type="family">Jaber</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 presents the PTUK-NLP submission to KnowledgeGraphEval 2026 Subtask 1 (AdaptNER), evaluating cross-domain and cross-dialect nested Arabic Named Entity Recognition (NER). Models trained on Wojood are evaluated in a zero-shot setting on Konooz, spanning ten unseen domains and sixteen Arabic dialects. Our system fine-tunes ArBERT with targeted augmentation for rare entity types and lightweight inference-time post-processing, using Konooz strictly for evaluation and never for training or adaptation. The submitted system achieves 91.07% micro-F1 and 83.11% macro-F1 on Wojood, and 71.84% precision, 66.59% recall, 69.11% micro-F1, and 60.70% macro-F1 on the official Konooz blind test, ranking fourth on the final leaderboard and achieving a micro-F1 score 6.11 points above the organizers’ baseline. A post-submission ensemble of ArBERT and AraBERTv2 does not improve over the best single model. Overall, targeted data-centric modifications provide useful gains for rare entity types, while a standard MSA-pretrained encoder remains competitive under substantial domain and dialect shift.</abstract>
<identifier type="citekey">duridi-etal-2026-ptuk</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.151/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1205</start>
<end>1211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PTUK-NLP at KnowledgeGraphEval 2026: Cross-Domain Nested Arabic NER with ArBERT and Targeted Data Augmentation
%A Duridi, Tasneem
%A Salih, Islam HJ
%A Jawabreh, Mariam
%A Jaber, Areej
%A Jaber, Elaa
%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 duridi-etal-2026-ptuk
%X This paper presents the PTUK-NLP submission to KnowledgeGraphEval 2026 Subtask 1 (AdaptNER), evaluating cross-domain and cross-dialect nested Arabic Named Entity Recognition (NER). Models trained on Wojood are evaluated in a zero-shot setting on Konooz, spanning ten unseen domains and sixteen Arabic dialects. Our system fine-tunes ArBERT with targeted augmentation for rare entity types and lightweight inference-time post-processing, using Konooz strictly for evaluation and never for training or adaptation. The submitted system achieves 91.07% micro-F1 and 83.11% macro-F1 on Wojood, and 71.84% precision, 66.59% recall, 69.11% micro-F1, and 60.70% macro-F1 on the official Konooz blind test, ranking fourth on the final leaderboard and achieving a micro-F1 score 6.11 points above the organizers’ baseline. A post-submission ensemble of ArBERT and AraBERTv2 does not improve over the best single model. Overall, targeted data-centric modifications provide useful gains for rare entity types, while a standard MSA-pretrained encoder remains competitive under substantial domain and dialect shift.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.151/
%P 1205-1211
Markdown (Informal)
[PTUK-NLP at KnowledgeGraphEval 2026: Cross-Domain Nested Arabic NER with ArBERT and Targeted Data Augmentation](https://aclanthology.org/2026.arabicnlp-sharedtasks.151/) (Duridi et al., ArabicNLP 2026)
ACL