@inproceedings{hamed-etal-2026-yafaner,
title = "{Y}afa{NER} at {K}nowledge{G}raph{E}val 2026: {A}ra{BERT}v2-based Approach to Cross-Domain Adaptation for {A}rabic {NER}",
author = "Hamed, Osama and
Melhem, Anas and
Qararia, Aseel and
Zerie, Sara",
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.156/",
pages = "1244--1249",
ISBN = "979-8-89176-497-2",
abstract = "Cross-domain Arabic Named Entity Recognition (NER) remains challenging because models trained on one domain can lose performance when applied to unseen domains with different vocabulary, writing styles, and entity distributions. This paper addresses this challenge, and presents Yafa{'}s Team submission (ranked $7^{th}$) to Subtask 1 of the KnowledgeGraphEval 2026 Shared Task. Our system leverages an AraBERTv2-based model for nested Arabic NER to approach it. The proposed approach combines task-adaptive (TAPT) pretraining on unlabeled Konooz data, R-Drop fine-tuning on Wojood, strong data augmentation, teacher-student knowledge distillation, span-level confidence and entropy filtering, and an entity-specific confidence-aware weighted-logit ensemble. Three teacher models generate soft labels for Konooz, and three distilled student models are combined in the final ensemble to produce the final predictions. Wojood contains approximately 448K tokens and 72K entity mentions across 21 entity types, while Konooz contains data from 10 domains for cross-domain evaluation. The final system achieves a Micro F1 of 71.33{\%} on the official Konooz test set, improving over the non-adapted AraBERTv02 baseline of 61.00{\%} by 10.33 points. The results show that combining domain adaptation, filtered knowledge transfer, and entity-specific ensembling can improve cross-domain Arabic NER performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamed-etal-2026-yafaner">
<titleInfo>
<title>YafaNER at KnowledgeGraphEval 2026: AraBERTv2-based Approach to Cross-Domain Adaptation for Arabic NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Osama</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anas</namePart>
<namePart type="family">Melhem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aseel</namePart>
<namePart type="family">Qararia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Zerie</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>Cross-domain Arabic Named Entity Recognition (NER) remains challenging because models trained on one domain can lose performance when applied to unseen domains with different vocabulary, writing styles, and entity distributions. This paper addresses this challenge, and presents Yafa’s Team submission (ranked 7^th) to Subtask 1 of the KnowledgeGraphEval 2026 Shared Task. Our system leverages an AraBERTv2-based model for nested Arabic NER to approach it. The proposed approach combines task-adaptive (TAPT) pretraining on unlabeled Konooz data, R-Drop fine-tuning on Wojood, strong data augmentation, teacher-student knowledge distillation, span-level confidence and entropy filtering, and an entity-specific confidence-aware weighted-logit ensemble. Three teacher models generate soft labels for Konooz, and three distilled student models are combined in the final ensemble to produce the final predictions. Wojood contains approximately 448K tokens and 72K entity mentions across 21 entity types, while Konooz contains data from 10 domains for cross-domain evaluation. The final system achieves a Micro F1 of 71.33% on the official Konooz test set, improving over the non-adapted AraBERTv02 baseline of 61.00% by 10.33 points. The results show that combining domain adaptation, filtered knowledge transfer, and entity-specific ensembling can improve cross-domain Arabic NER performance.</abstract>
<identifier type="citekey">hamed-etal-2026-yafaner</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.156/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1244</start>
<end>1249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YafaNER at KnowledgeGraphEval 2026: AraBERTv2-based Approach to Cross-Domain Adaptation for Arabic NER
%A Hamed, Osama
%A Melhem, Anas
%A Qararia, Aseel
%A Zerie, Sara
%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 hamed-etal-2026-yafaner
%X Cross-domain Arabic Named Entity Recognition (NER) remains challenging because models trained on one domain can lose performance when applied to unseen domains with different vocabulary, writing styles, and entity distributions. This paper addresses this challenge, and presents Yafa’s Team submission (ranked 7^th) to Subtask 1 of the KnowledgeGraphEval 2026 Shared Task. Our system leverages an AraBERTv2-based model for nested Arabic NER to approach it. The proposed approach combines task-adaptive (TAPT) pretraining on unlabeled Konooz data, R-Drop fine-tuning on Wojood, strong data augmentation, teacher-student knowledge distillation, span-level confidence and entropy filtering, and an entity-specific confidence-aware weighted-logit ensemble. Three teacher models generate soft labels for Konooz, and three distilled student models are combined in the final ensemble to produce the final predictions. Wojood contains approximately 448K tokens and 72K entity mentions across 21 entity types, while Konooz contains data from 10 domains for cross-domain evaluation. The final system achieves a Micro F1 of 71.33% on the official Konooz test set, improving over the non-adapted AraBERTv02 baseline of 61.00% by 10.33 points. The results show that combining domain adaptation, filtered knowledge transfer, and entity-specific ensembling can improve cross-domain Arabic NER performance.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.156/
%P 1244-1249
Markdown (Informal)
[YafaNER at KnowledgeGraphEval 2026: AraBERTv2-based Approach to Cross-Domain Adaptation for Arabic NER](https://aclanthology.org/2026.arabicnlp-sharedtasks.156/) (Hamed et al., ArabicNLP 2026)
ACL