@inproceedings{real-de-paiva-2026-opencor,
title = "{O}pen{C}or: {L}atin {A}merican and {I}berian Languages Open Corpora Forum",
author = "Real, Livy and
de Paiva, Valeria",
editor = "Claramunt, German Rigau and
Gamallo, Pablo and
Mu{\~n}oz Guillena, Rafael and
Chiruzzo, Luis and
Mart{\'i}nez C{\'a}mara, Eugenio",
booktitle = "Proceedings of {LANLP}: Bridging {I}bero and {L}atin {A}merican {NLP} Communities",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lanlp-1.4/",
doi = "10.63317/42vgyuuoduhr",
pages = "21--28",
abstract = "The availability of open resources and corpora is a fundamental requirement for research in Natural Language Processing (NLP) and Computational Linguistics; however, languages spoken in Latin America and the Iberian Peninsula, particularly Indigenous, minority, and regional varieties, remain structurally under-resourced and under-represented. This paper presents a historical account of OpenCor (Latin American and Iberian Languages Open Corpora Forum), a community-driven initiative created to promote, document, and discuss open linguistic corpora and lexical resources for these languages. Conceived as a collaborative forum rather than a competitive evaluation venue, OpenCor focuses on data creation, licensing practices, sustainability, and community building. Between 2018 and 2024, OpenCor was organized as a recurring workshop co-located with major conferences, fostering dialogue across countries, institutions, and linguistic traditions. By documenting the initiative{'}s motivations, organizational trajectory, submission trends, and the diversity of resources presented, this paper aims to preserve institutional memory, highlight the often-invisible labor of corpus development, and provide a reference for future initiatives dedicated to openness and linguistic diversity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="real-de-paiva-2026-opencor">
<titleInfo>
<title>OpenCor: Latin American and Iberian Languages Open Corpora Forum</title>
</titleInfo>
<name type="personal">
<namePart type="given">Livy</namePart>
<namePart type="family">Real</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valeria</namePart>
<namePart type="family">de Paiva</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 LANLP: Bridging Ibero and Latin American NLP Communities</title>
</titleInfo>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Gamallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Muñoz Guillena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugenio</namePart>
<namePart type="family">Martínez Cámara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The availability of open resources and corpora is a fundamental requirement for research in Natural Language Processing (NLP) and Computational Linguistics; however, languages spoken in Latin America and the Iberian Peninsula, particularly Indigenous, minority, and regional varieties, remain structurally under-resourced and under-represented. This paper presents a historical account of OpenCor (Latin American and Iberian Languages Open Corpora Forum), a community-driven initiative created to promote, document, and discuss open linguistic corpora and lexical resources for these languages. Conceived as a collaborative forum rather than a competitive evaluation venue, OpenCor focuses on data creation, licensing practices, sustainability, and community building. Between 2018 and 2024, OpenCor was organized as a recurring workshop co-located with major conferences, fostering dialogue across countries, institutions, and linguistic traditions. By documenting the initiative’s motivations, organizational trajectory, submission trends, and the diversity of resources presented, this paper aims to preserve institutional memory, highlight the often-invisible labor of corpus development, and provide a reference for future initiatives dedicated to openness and linguistic diversity.</abstract>
<identifier type="citekey">real-de-paiva-2026-opencor</identifier>
<identifier type="doi">10.63317/42vgyuuoduhr</identifier>
<location>
<url>https://aclanthology.org/2026.lanlp-1.4/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>21</start>
<end>28</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenCor: Latin American and Iberian Languages Open Corpora Forum
%A Real, Livy
%A de Paiva, Valeria
%Y Claramunt, German Rigau
%Y Gamallo, Pablo
%Y Muñoz Guillena, Rafael
%Y Chiruzzo, Luis
%Y Martínez Cámara, Eugenio
%S Proceedings of LANLP: Bridging Ibero and Latin American NLP Communities
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F real-de-paiva-2026-opencor
%X The availability of open resources and corpora is a fundamental requirement for research in Natural Language Processing (NLP) and Computational Linguistics; however, languages spoken in Latin America and the Iberian Peninsula, particularly Indigenous, minority, and regional varieties, remain structurally under-resourced and under-represented. This paper presents a historical account of OpenCor (Latin American and Iberian Languages Open Corpora Forum), a community-driven initiative created to promote, document, and discuss open linguistic corpora and lexical resources for these languages. Conceived as a collaborative forum rather than a competitive evaluation venue, OpenCor focuses on data creation, licensing practices, sustainability, and community building. Between 2018 and 2024, OpenCor was organized as a recurring workshop co-located with major conferences, fostering dialogue across countries, institutions, and linguistic traditions. By documenting the initiative’s motivations, organizational trajectory, submission trends, and the diversity of resources presented, this paper aims to preserve institutional memory, highlight the often-invisible labor of corpus development, and provide a reference for future initiatives dedicated to openness and linguistic diversity.
%R 10.63317/42vgyuuoduhr
%U https://aclanthology.org/2026.lanlp-1.4/
%U https://doi.org/10.63317/42vgyuuoduhr
%P 21-28
Markdown (Informal)
[OpenCor: Latin American and Iberian Languages Open Corpora Forum](https://aclanthology.org/2026.lanlp-1.4/) (Real & de Paiva, LANLP 2026)
ACL