@inproceedings{arranz-etal-2026-euskorpora,
title = "Euskorpora: A Strategic Framework for Digital Sovereignty and Linguistic Inclusion of {B}asque in the Era of {AI}",
author = "Arranz, Victoria and
Arregi, Sara and
Bara{\~n}ano, Leire and
Garc{\'i}a-Pablos, Aitor",
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-1.93/",
doi = "10.63317/4azrgurn3893",
pages = "1189--1196",
abstract = "Euskorpora is a pioneering initiative designed to establish a comprehensive digital infrastructure for the development of speech and language technologies in Basque. Built upon European, Spanish, and Basque strategies, it addresses the scarcity of linguistic data, foundational models, and technological resources for this non-Indo-European, low-resourced language. The project integrates large-scale data collection from public institutions and private organisations, creating extensive multimodal corpora that cover the linguistic, dialectal, and domain diversity of Basque. These resources support the training of open language models for speech, translation, and language understanding, as well as the establishment of an interoperable infrastructure aligned with European initiatives such as the European Language Data Space (LDS). By combining linguistic research, artificial intelligence, and data governance, Euskorpora ensures the digital sovereignty and inclusion of the Basque language within the global AI ecosystem. Beyond its regional focus, it stands as a transferable model for advancing linguistic diversity, technological innovation, and equitable digital transformation in multilingual Europe."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arranz-etal-2026-euskorpora">
<titleInfo>
<title>Euskorpora: A Strategic Framework for Digital Sovereignty and Linguistic Inclusion of Basque in the Era of AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Arranz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Arregi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leire</namePart>
<namePart type="family">Barañano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">García-Pablos</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>Euskorpora is a pioneering initiative designed to establish a comprehensive digital infrastructure for the development of speech and language technologies in Basque. Built upon European, Spanish, and Basque strategies, it addresses the scarcity of linguistic data, foundational models, and technological resources for this non-Indo-European, low-resourced language. The project integrates large-scale data collection from public institutions and private organisations, creating extensive multimodal corpora that cover the linguistic, dialectal, and domain diversity of Basque. These resources support the training of open language models for speech, translation, and language understanding, as well as the establishment of an interoperable infrastructure aligned with European initiatives such as the European Language Data Space (LDS). By combining linguistic research, artificial intelligence, and data governance, Euskorpora ensures the digital sovereignty and inclusion of the Basque language within the global AI ecosystem. Beyond its regional focus, it stands as a transferable model for advancing linguistic diversity, technological innovation, and equitable digital transformation in multilingual Europe.</abstract>
<identifier type="citekey">arranz-etal-2026-euskorpora</identifier>
<identifier type="doi">10.63317/4azrgurn3893</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.93/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1189</start>
<end>1196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Euskorpora: A Strategic Framework for Digital Sovereignty and Linguistic Inclusion of Basque in the Era of AI
%A Arranz, Victoria
%A Arregi, Sara
%A Barañano, Leire
%A García-Pablos, Aitor
%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 arranz-etal-2026-euskorpora
%X Euskorpora is a pioneering initiative designed to establish a comprehensive digital infrastructure for the development of speech and language technologies in Basque. Built upon European, Spanish, and Basque strategies, it addresses the scarcity of linguistic data, foundational models, and technological resources for this non-Indo-European, low-resourced language. The project integrates large-scale data collection from public institutions and private organisations, creating extensive multimodal corpora that cover the linguistic, dialectal, and domain diversity of Basque. These resources support the training of open language models for speech, translation, and language understanding, as well as the establishment of an interoperable infrastructure aligned with European initiatives such as the European Language Data Space (LDS). By combining linguistic research, artificial intelligence, and data governance, Euskorpora ensures the digital sovereignty and inclusion of the Basque language within the global AI ecosystem. Beyond its regional focus, it stands as a transferable model for advancing linguistic diversity, technological innovation, and equitable digital transformation in multilingual Europe.
%R 10.63317/4azrgurn3893
%U https://aclanthology.org/2026.lrec-1.93/
%U https://doi.org/10.63317/4azrgurn3893
%P 1189-1196
Markdown (Informal)
[Euskorpora: A Strategic Framework for Digital Sovereignty and Linguistic Inclusion of Basque in the Era of AI](https://aclanthology.org/2026.lrec-1.93/) (Arranz et al., LREC 2026)
ACL