@inproceedings{palomar-giner-etal-2024-curated,
    title = "A {CURATE}d {CAT}alog: Rethinking the Extraction of Pretraining Corpora for Mid-Resourced Languages",
    author = "Palomar-Giner, Jorge  and
      Saiz, Jose Javier  and
      Espu{\~n}a, Ferran  and
      Mina, Mario  and
      Da Dalt, Severino  and
      Llop, Joan  and
      Ostendorff, Malte  and
      Ortiz Suarez, Pedro  and
      Rehm, Georg  and
      Gonzalez-Agirre, Aitor  and
      Villegas, Marta",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.lrec-main.31/",
    pages = "335--349"
}