@inproceedings{bouzaiene-etal-2026-anlp,
title = "{ANLP}{\_}{U}ni{S}o at {K}nowledge{G}raph{E}val 2026: Domain-Adaptive Nested Named Entity Recognition for {A}rabic via {G}lobal{P}ointer Ensembling",
author = "Bouzaiene, Eya and
Trigui, Omar and
Belguith, Lamia",
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.157/",
pages = "1250--1254",
ISBN = "979-8-89176-497-2",
abstract = "The ANLP{\_}UniSo team submitted a system to Subtask 1 (Named Entity Recognition) of KnowledgeGraphEval 2026, which focuses on nested NER in Arabic and evaluates crossdomain and cross-dialect generalization from the Wojood corpus to the multi-domain Konooz benchmark. The system is a combination of an Efficient GlobalPointer decoder with rotary position embeddings and a MARBERT backbone. To reduce the domain gap, first domainadaptive pretraining (DAPT) is performed on unlabeled Konooz text, and then a pseudolabeling self-training stage is applied. A second model based on AraBERT is trained and combined to the other model using a stacking ensemble to improve prediction diversity. As for the Wojood test set, the best ensemble achieves a micro F1 of 0.9288, increasing to 0.9292 when entity-type-specific decision thresholds are used, compared with 0.9211 for the single MARBERT model. On the official blind Konooz test set, however, the submitted system obtains a micro F1 of 0.7106 (macro F1 = 0.6101, weighted F1 = 0.7013, P = 0.8143, R = 0.6304, accuracy = 0.9948). The lower recall suggests that the decoding threshold chosen based on the Wojood validation data was too strict for the domain-shifted Konooz data. the system study the difference and propose a threshold-recalibration strategy to improve the performance under the target-domain distribution."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bouzaiene-etal-2026-anlp">
<titleInfo>
<title>ANLP_UniSo at KnowledgeGraphEval 2026: Domain-Adaptive Nested Named Entity Recognition for Arabic via GlobalPointer Ensembling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eya</namePart>
<namePart type="family">Bouzaiene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Trigui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="family">Belguith</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>The ANLP_UniSo team submitted a system to Subtask 1 (Named Entity Recognition) of KnowledgeGraphEval 2026, which focuses on nested NER in Arabic and evaluates crossdomain and cross-dialect generalization from the Wojood corpus to the multi-domain Konooz benchmark. The system is a combination of an Efficient GlobalPointer decoder with rotary position embeddings and a MARBERT backbone. To reduce the domain gap, first domainadaptive pretraining (DAPT) is performed on unlabeled Konooz text, and then a pseudolabeling self-training stage is applied. A second model based on AraBERT is trained and combined to the other model using a stacking ensemble to improve prediction diversity. As for the Wojood test set, the best ensemble achieves a micro F1 of 0.9288, increasing to 0.9292 when entity-type-specific decision thresholds are used, compared with 0.9211 for the single MARBERT model. On the official blind Konooz test set, however, the submitted system obtains a micro F1 of 0.7106 (macro F1 = 0.6101, weighted F1 = 0.7013, P = 0.8143, R = 0.6304, accuracy = 0.9948). The lower recall suggests that the decoding threshold chosen based on the Wojood validation data was too strict for the domain-shifted Konooz data. the system study the difference and propose a threshold-recalibration strategy to improve the performance under the target-domain distribution.</abstract>
<identifier type="citekey">bouzaiene-etal-2026-anlp</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.157/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1250</start>
<end>1254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ANLP_UniSo at KnowledgeGraphEval 2026: Domain-Adaptive Nested Named Entity Recognition for Arabic via GlobalPointer Ensembling
%A Bouzaiene, Eya
%A Trigui, Omar
%A Belguith, Lamia
%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 bouzaiene-etal-2026-anlp
%X The ANLP_UniSo team submitted a system to Subtask 1 (Named Entity Recognition) of KnowledgeGraphEval 2026, which focuses on nested NER in Arabic and evaluates crossdomain and cross-dialect generalization from the Wojood corpus to the multi-domain Konooz benchmark. The system is a combination of an Efficient GlobalPointer decoder with rotary position embeddings and a MARBERT backbone. To reduce the domain gap, first domainadaptive pretraining (DAPT) is performed on unlabeled Konooz text, and then a pseudolabeling self-training stage is applied. A second model based on AraBERT is trained and combined to the other model using a stacking ensemble to improve prediction diversity. As for the Wojood test set, the best ensemble achieves a micro F1 of 0.9288, increasing to 0.9292 when entity-type-specific decision thresholds are used, compared with 0.9211 for the single MARBERT model. On the official blind Konooz test set, however, the submitted system obtains a micro F1 of 0.7106 (macro F1 = 0.6101, weighted F1 = 0.7013, P = 0.8143, R = 0.6304, accuracy = 0.9948). The lower recall suggests that the decoding threshold chosen based on the Wojood validation data was too strict for the domain-shifted Konooz data. the system study the difference and propose a threshold-recalibration strategy to improve the performance under the target-domain distribution.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.157/
%P 1250-1254
Markdown (Informal)
[ANLP_UniSo at KnowledgeGraphEval 2026: Domain-Adaptive Nested Named Entity Recognition for Arabic via GlobalPointer Ensembling](https://aclanthology.org/2026.arabicnlp-sharedtasks.157/) (Bouzaiene et al., ArabicNLP 2026)
ACL