@inproceedings{zhang-2026-pages,
    title = "Same Pages, Cleaner Labels: Language Identification for Eight Low-Resource Languages in m{C}4 and {F}ine{W}eb-2",
    author = "Zhang, Gary",
    editor = "Ortiz Suarez, Pedro  and
      Burchell, Laurie  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Scherrer, Yves  and
      Laippala, Veronika  and
      Dini{\'c}, Vuk  and
      Vaughan, Thom",
    booktitle = "Proceedings of the 13th Web-as-Corpus Workshop",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.wac-1.15/",
    pages = "161--169",
    ISBN = "979-8-89176-481-1"
}