@inproceedings{karaosmanoglu-2026-extraction,
    title = "Extraction Changes the Route: Main-Content Extraction and Language Identification in Web Corpora",
    author = "Karaosmano{\u{g}}lu, Toprak Seda",
    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-1.26/",
    pages = "297--307",
    ISBN = "979-8-89176-481-1"
}