@inproceedings{zhang-2026-lost, title = "Lost in Translation: Structured-Span Corruption in Machine-Translated Multilingual Web Corpora", author = "Zhang, Ruiyang", 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-1.9/", pages = "100--106", ISBN = "979-8-89176-481-1" }