@inproceedings{bengoetxea-etal-2026-catalog,
title = "A Catalog of {B}asque Dialectal Resources: Online Collections and Standard-to-Dialectal Adaptations",
author = "Bengoetxea, Jaione and
Gonzalez-Dios, Itziar and
Agerri, Rodrigo",
editor = "Anastasopoulos, Antonis and
Markantonatou, Stella and
Ralli, Angela and
Zampieri, Marcos and
Bompolas, Stavros and
Stamou, Vivian",
booktitle = "Proceedings of the First Workshop on Dialects in {NLP} {---} A Resource Perspective",
month = may,
year = "2026",
address = "Palma de Mallorca",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.dialres-1.16/",
doi = "10.63317/3zhrab5powcg",
pages = "153--164",
abstract = "Recent research on dialectal NLP has identified data scarcity as a primary limitation. To address this limitation, this paper presents a catalog of contemporary Basque dialectal data and resources, offering a systematic and comprehensive compilation of the dialectal data currently available in Basque. Two types of data sources have been distinguished: online data originally written in some dialect, and standard-to-dialect adapted data. The former includes all dialectal data that can be found online, such as news and radio sites, informal tweets, as well as online resources such as dictionaries, atlases, grammar rules, or videos. The latter consists of data that has been adapted from the standard variety to dialectal varieties, either manually or automatically. Regarding the manual adaptation, the test split of the XNLI Natural Language Inference dataset was manually adapted into three Basque dialects: Western, Central, and Navarrese-Lapurdian, yielding a high-quality parallel gold standard evaluation dataset. With respect to the automatic dialectal adaptation, the automatically adapted physical commonsense dataset (BasPhyCowest) underwent additional manual evaluation by native speakers to assess its quality and determine whether it could serve as a viable substitute for full manual adaptation (i.e., silver data creation)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bengoetxea-etal-2026-catalog">
<titleInfo>
<title>A Catalog of Basque Dialectal Resources: Online Collections and Standard-to-Dialectal Adaptations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaione</namePart>
<namePart type="family">Bengoetxea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itziar</namePart>
<namePart type="family">Gonzalez-Dios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Agerri</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 First Workshop on Dialects in NLP — A Resource Perspective</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonis</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stella</namePart>
<namePart type="family">Markantonatou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Ralli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stavros</namePart>
<namePart type="family">Bompolas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Stamou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma de Mallorca</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent research on dialectal NLP has identified data scarcity as a primary limitation. To address this limitation, this paper presents a catalog of contemporary Basque dialectal data and resources, offering a systematic and comprehensive compilation of the dialectal data currently available in Basque. Two types of data sources have been distinguished: online data originally written in some dialect, and standard-to-dialect adapted data. The former includes all dialectal data that can be found online, such as news and radio sites, informal tweets, as well as online resources such as dictionaries, atlases, grammar rules, or videos. The latter consists of data that has been adapted from the standard variety to dialectal varieties, either manually or automatically. Regarding the manual adaptation, the test split of the XNLI Natural Language Inference dataset was manually adapted into three Basque dialects: Western, Central, and Navarrese-Lapurdian, yielding a high-quality parallel gold standard evaluation dataset. With respect to the automatic dialectal adaptation, the automatically adapted physical commonsense dataset (BasPhyCowest) underwent additional manual evaluation by native speakers to assess its quality and determine whether it could serve as a viable substitute for full manual adaptation (i.e., silver data creation).</abstract>
<identifier type="citekey">bengoetxea-etal-2026-catalog</identifier>
<identifier type="doi">10.63317/3zhrab5powcg</identifier>
<location>
<url>https://aclanthology.org/2026.dialres-1.16/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>153</start>
<end>164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Catalog of Basque Dialectal Resources: Online Collections and Standard-to-Dialectal Adaptations
%A Bengoetxea, Jaione
%A Gonzalez-Dios, Itziar
%A Agerri, Rodrigo
%Y Anastasopoulos, Antonis
%Y Markantonatou, Stella
%Y Ralli, Angela
%Y Zampieri, Marcos
%Y Bompolas, Stavros
%Y Stamou, Vivian
%S Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma de Mallorca
%F bengoetxea-etal-2026-catalog
%X Recent research on dialectal NLP has identified data scarcity as a primary limitation. To address this limitation, this paper presents a catalog of contemporary Basque dialectal data and resources, offering a systematic and comprehensive compilation of the dialectal data currently available in Basque. Two types of data sources have been distinguished: online data originally written in some dialect, and standard-to-dialect adapted data. The former includes all dialectal data that can be found online, such as news and radio sites, informal tweets, as well as online resources such as dictionaries, atlases, grammar rules, or videos. The latter consists of data that has been adapted from the standard variety to dialectal varieties, either manually or automatically. Regarding the manual adaptation, the test split of the XNLI Natural Language Inference dataset was manually adapted into three Basque dialects: Western, Central, and Navarrese-Lapurdian, yielding a high-quality parallel gold standard evaluation dataset. With respect to the automatic dialectal adaptation, the automatically adapted physical commonsense dataset (BasPhyCowest) underwent additional manual evaluation by native speakers to assess its quality and determine whether it could serve as a viable substitute for full manual adaptation (i.e., silver data creation).
%R 10.63317/3zhrab5powcg
%U https://aclanthology.org/2026.dialres-1.16/
%U https://doi.org/10.63317/3zhrab5powcg
%P 153-164
Markdown (Informal)
[A Catalog of Basque Dialectal Resources: Online Collections and Standard-to-Dialectal Adaptations](https://aclanthology.org/2026.dialres-1.16/) (Bengoetxea et al., DialRes 2026)
ACL