@inproceedings{razzaghi-etal-2026-hplt3, title = "{HPLT}3-{P}er{R}ef: A Refined Large-Scale {P}ersian Web Corpus via Supervised Document Quality Filtering", author = "Razzaghi, Alireza and Galica, Tomasz and Henriksson, Erik and Laippala, Veronika", 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-1.6/", pages = "60--69", ISBN = "979-8-89176-481-1" }