@inproceedings{de-jesus-nunes-2024-data,
    title = "Data Collection Pipeline for Low-Resource Languages: A Case Study on Constructing a Tetun Text Corpus",
    author = "de Jesus, Gabriel  and
      Nunes, S{\'e}rgio Sobral",
    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/fix-sig-urls/2024.lrec-main.390/",
    pages = "4368--4380"
}