@inproceedings{eldamaty-etal-2026-efficient,
title = "Efficient Adaptation of {E}nglish Language Models for Morphologically Rich and Underrepresented Languages: The Case of {A}rabic",
author = "Eldamaty, Ahmed Samy and
Abdelrahman, Mohamed Maher Zenhom and
Elbehery, Mohamed Mostafa Ibrahim and
Ashraf, Mariam and
Elshawi, Radwa",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.822/",
doi = "10.63317/3xdz933rn47i",
pages = "10485--10496",
abstract = "Transformer-based language models have revolutionized NLP, yet their adaptation to morphologically rich and dialectally diverse languages such as Arabic remains non-trivial. We introduce ModernAraBERT, a resource-efficient adaptation of the English-pretrained ModernBERT for Arabic, employing continued pretraining on large Arabic corpora followed by lightweight head-only fine-tuning with a frozen encoder. This strategy retains cross-lingual knowledge while capturing Arabic morphology and orthographic variation, offering a scalable alternative to training monolingual models from scratch. We evaluate ModernAraBERT on three representative Arabic NLP tasks, sentiment analysis, named entity recognition, and extractive question answering, against strong Arabic-specific and multilingual baselines (AraBERTv1, AraBERTv2, MARBERT, mBERT). Across all tasks, ModernAraBERT achieves consistent and often substantial improvements, particularly for sentence and token-level understanding, demonstrating that modern English encoder architectures can be efficiently transferred to Arabic through language-adaptive pretraining. Beyond Arabic, our findings highlight a generalizable paradigm for extending state-of-the-art models to morphologically complex and underrepresented languages with reduced computational overhead."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eldamaty-etal-2026-efficient">
<titleInfo>
<title>Efficient Adaptation of English Language Models for Morphologically Rich and Underrepresented Languages: The Case of Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Samy</namePart>
<namePart type="family">Eldamaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Maher</namePart>
<namePart type="given">Zenhom</namePart>
<namePart type="family">Abdelrahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Mostafa</namePart>
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Elbehery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="family">Ashraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radwa</namePart>
<namePart type="family">Elshawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transformer-based language models have revolutionized NLP, yet their adaptation to morphologically rich and dialectally diverse languages such as Arabic remains non-trivial. We introduce ModernAraBERT, a resource-efficient adaptation of the English-pretrained ModernBERT for Arabic, employing continued pretraining on large Arabic corpora followed by lightweight head-only fine-tuning with a frozen encoder. This strategy retains cross-lingual knowledge while capturing Arabic morphology and orthographic variation, offering a scalable alternative to training monolingual models from scratch. We evaluate ModernAraBERT on three representative Arabic NLP tasks, sentiment analysis, named entity recognition, and extractive question answering, against strong Arabic-specific and multilingual baselines (AraBERTv1, AraBERTv2, MARBERT, mBERT). Across all tasks, ModernAraBERT achieves consistent and often substantial improvements, particularly for sentence and token-level understanding, demonstrating that modern English encoder architectures can be efficiently transferred to Arabic through language-adaptive pretraining. Beyond Arabic, our findings highlight a generalizable paradigm for extending state-of-the-art models to morphologically complex and underrepresented languages with reduced computational overhead.</abstract>
<identifier type="citekey">eldamaty-etal-2026-efficient</identifier>
<identifier type="doi">10.63317/3xdz933rn47i</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.822/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10485</start>
<end>10496</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Adaptation of English Language Models for Morphologically Rich and Underrepresented Languages: The Case of Arabic
%A Eldamaty, Ahmed Samy
%A Abdelrahman, Mohamed Maher Zenhom
%A Elbehery, Mohamed Mostafa Ibrahim
%A Ashraf, Mariam
%A Elshawi, Radwa
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F eldamaty-etal-2026-efficient
%X Transformer-based language models have revolutionized NLP, yet their adaptation to morphologically rich and dialectally diverse languages such as Arabic remains non-trivial. We introduce ModernAraBERT, a resource-efficient adaptation of the English-pretrained ModernBERT for Arabic, employing continued pretraining on large Arabic corpora followed by lightweight head-only fine-tuning with a frozen encoder. This strategy retains cross-lingual knowledge while capturing Arabic morphology and orthographic variation, offering a scalable alternative to training monolingual models from scratch. We evaluate ModernAraBERT on three representative Arabic NLP tasks, sentiment analysis, named entity recognition, and extractive question answering, against strong Arabic-specific and multilingual baselines (AraBERTv1, AraBERTv2, MARBERT, mBERT). Across all tasks, ModernAraBERT achieves consistent and often substantial improvements, particularly for sentence and token-level understanding, demonstrating that modern English encoder architectures can be efficiently transferred to Arabic through language-adaptive pretraining. Beyond Arabic, our findings highlight a generalizable paradigm for extending state-of-the-art models to morphologically complex and underrepresented languages with reduced computational overhead.
%R 10.63317/3xdz933rn47i
%U https://aclanthology.org/2026.lrec-1.822/
%U https://doi.org/10.63317/3xdz933rn47i
%P 10485-10496
Markdown (Informal)
[Efficient Adaptation of English Language Models for Morphologically Rich and Underrepresented Languages: The Case of Arabic](https://aclanthology.org/2026.lrec-1.822/) (Eldamaty et al., LREC 2026)
ACL