@inproceedings{yang-lin-2020-tocp,
    title = "{TOCP}: A Dataset for {C}hinese Profanity Processing",
    author = "Yang, Hsu  and
      Lin, Chuan-Jie",
    editor = "Kumar, Ritesh  and
      Ojha, Atul Kr.  and
      Lahiri, Bornini  and
      Zampieri, Marcos  and
      Malmasi, Shervin  and
      Murdock, Vanessa  and
      Kadar, Daniel",
    booktitle = "Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2020.trac-1.2",
    pages = "6--12",
    abstract = "This paper introduced TOCP, a larger dataset of Chinese profanity. This dataset contains natural sentences collected from social media sites, the profane expressions appearing in the sentences, and their rephrasing suggestions which preserve their meanings in a less offensive way. We proposed several baseline systems using neural network models to test this benchmark. We trained embedding models on a profanity-related dataset and proposed several profanity-related features. Our baseline systems achieved an F1-score of 86.37{\%} in profanity detection and an accuracy of 77.32{\%} in profanity rephrasing.",
    language = "English",
    ISBN = "979-10-95546-56-6",
}