@inproceedings{luccioni-viviano-2021-whats,
    title = "What{'}s in the Box? An Analysis of Undesirable Content in the {C}ommon {C}rawl Corpus",
    author = "Luccioni, Alexandra  and
      Viviano, Joseph",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.acl-short.24/",
    doi = "10.18653/v1/2021.acl-short.24",
    pages = "182--189"
}