@inproceedings{enomoto-etal-2024-investigating,
    title = "Investigating Web Corpus Filtering Methods for Language Model Development in {J}apanese",
    author = "Enomoto, Rintaro  and
      Tolmachev, Arseny  and
      Niitsuma, Takuro  and
      Kurita, Shuhei  and
      Kawahara, Daisuke",
    editor = "Cao, Yang (Trista)  and
      Papadimitriou, Isabel  and
      Ovalle, Anaelia  and
      Zampieri, Marcos  and
      Ferraro, Francis  and
      Swayamdipta, Swabha",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-srw.18/",
    doi = "10.18653/v1/2024.naacl-srw.18",
    pages = "154--160"
}