@inproceedings{zingano-kuhn-etal-2026-corege,
title = "{C}or{EG}e-{PT}: Compiling a Large Corpus of Academic Texts in{~}{P}ortuguese",
author = "Zingano Kuhn, Tanara and
Matos, Jos{\'e} and
Neves, Bruno and
Pereira, Daniela and
Ca{\c{c}}{\~a}o, Elisabete and
Sim{\~o}es, Ivo and
Estima, Jacinto and
Le{\~a}o, Delfim and
Goncalo Oliveira, Hugo",
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-1.118/",
doi = "10.63317/3wm6ywh8gzxm",
pages = "1533--1543",
abstract = "This paper describes the creation of a large-scale corpus of academic texts in Portuguese, dubbed CorEGe-PT, extracted from the institutional repository of a Portuguese university. Its compilation methodology, which combined automatic and manual procedures, is detailed, together with challenges faced and proposed solutions. The process included a thorough analysis of the metadata, which will be publicly released together with the documents, extracted in a markdown format. CorEGe-PT covers five areas of knowledge and, with over 34,000 documents and 1B tokens, is the largest of corpus of its kind in Portuguese, which will enable in-depth linguistic studies while providing data for adapting Large Language Models to academic Portuguese and related tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zingano-kuhn-etal-2026-corege">
<titleInfo>
<title>CorEGe-PT: Compiling a Large Corpus of Academic Texts in Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanara</namePart>
<namePart type="family">Zingano Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="family">Matos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Pereira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisabete</namePart>
<namePart type="family">Cação</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivo</namePart>
<namePart type="family">Simões</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacinto</namePart>
<namePart type="family">Estima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Delfim</namePart>
<namePart type="family">Leão</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Goncalo Oliveira</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>This paper describes the creation of a large-scale corpus of academic texts in Portuguese, dubbed CorEGe-PT, extracted from the institutional repository of a Portuguese university. Its compilation methodology, which combined automatic and manual procedures, is detailed, together with challenges faced and proposed solutions. The process included a thorough analysis of the metadata, which will be publicly released together with the documents, extracted in a markdown format. CorEGe-PT covers five areas of knowledge and, with over 34,000 documents and 1B tokens, is the largest of corpus of its kind in Portuguese, which will enable in-depth linguistic studies while providing data for adapting Large Language Models to academic Portuguese and related tasks.</abstract>
<identifier type="citekey">zingano-kuhn-etal-2026-corege</identifier>
<identifier type="doi">10.63317/3wm6ywh8gzxm</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.118/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1533</start>
<end>1543</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CorEGe-PT: Compiling a Large Corpus of Academic Texts in Portuguese
%A Zingano Kuhn, Tanara
%A Matos, José
%A Neves, Bruno
%A Pereira, Daniela
%A Cação, Elisabete
%A Simões, Ivo
%A Estima, Jacinto
%A Leão, Delfim
%A Goncalo Oliveira, Hugo
%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 zingano-kuhn-etal-2026-corege
%X This paper describes the creation of a large-scale corpus of academic texts in Portuguese, dubbed CorEGe-PT, extracted from the institutional repository of a Portuguese university. Its compilation methodology, which combined automatic and manual procedures, is detailed, together with challenges faced and proposed solutions. The process included a thorough analysis of the metadata, which will be publicly released together with the documents, extracted in a markdown format. CorEGe-PT covers five areas of knowledge and, with over 34,000 documents and 1B tokens, is the largest of corpus of its kind in Portuguese, which will enable in-depth linguistic studies while providing data for adapting Large Language Models to academic Portuguese and related tasks.
%R 10.63317/3wm6ywh8gzxm
%U https://aclanthology.org/2026.lrec-1.118/
%U https://doi.org/10.63317/3wm6ywh8gzxm
%P 1533-1543
Markdown (Informal)
[CorEGe-PT: Compiling a Large Corpus of Academic Texts in Portuguese](https://aclanthology.org/2026.lrec-1.118/) (Zingano Kuhn et al., LREC 2026)
ACL
- Tanara Zingano Kuhn, José Matos, Bruno Neves, Daniela Pereira, Elisabete Cação, Ivo Simões, Jacinto Estima, Delfim Leão, and Hugo Goncalo Oliveira. 2026. CorEGe-PT: Compiling a Large Corpus of Academic Texts in Portuguese. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1533–1543, Palma de Mallorca, Spain. ELRA Language Resource Association.