@article{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",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.118/",
    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."
}