@inproceedings{chernyak-2017-comparison,
    title = "Comparison of String Similarity Measures for Obscenity Filtering",
    author = "Chernyak, Ekaterina",
    editor = "Erjavec, Toma{\v{z}}  and
      Piskorski, Jakub  and
      Pivovarova, Lidia  and
      {\v{S}}najder, Jan  and
      Steinberger, Josef  and
      Yangarber, Roman",
    booktitle = "Proceedings of the 6th Workshop on {B}alto-{S}lavic Natural Language Processing",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W17-1415/",
    doi = "10.18653/v1/W17-1415",
    pages = "97--101",
    abstract = "In this paper we address the problem of filtering obscene lexis in Russian texts. We use string similarity measures to find words similar or identical to words from a stop list and establish both a test collection and a baseline for the task. Our experiments show that a novel string similarity measure based on the notion of an annotated suffix tree outperforms some of the other well known measures."
}