@inproceedings{dent-etal-2025-identifying,
    title = "Identifying Rare Languages in {C}ommon {C}rawl Data is a Needles-in-a-Haystack Problem",
    author = "Dent, Rasul  and
      Ortiz Suarez, Pedro  and
      Cl{\'e}rice, Thibault  and
      Sagot, Beno{\^i}t",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.77/",
    pages = "1460--1473",
    ISBN = "979-8-89176-335-7"
}