@inproceedings{sahlgren-etal-2018-learning,
    title = "Learning Representations for Detecting Abusive Language",
    author = "Sahlgren, Magnus  and
      Isbister, Tim  and
      Olsson, Fredrik",
    editor = "Fi{\v{s}}er, Darja  and
      Huang, Ruihong  and
      Prabhakaran, Vinodkumar  and
      Voigt, Rob  and
      Waseem, Zeerak  and
      Wernimont, Jacqueline",
    booktitle = "Proceedings of the 2nd Workshop on Abusive Language Online ({ALW}2)",
    month = oct,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/W18-5115/",
    doi = "10.18653/v1/W18-5115",
    pages = "115--123",
    abstract = "This paper discusses the question whether it is possible to learn a generic representation that is useful for detecting various types of abusive language. The approach is inspired by recent advances in transfer learning and word embeddings, and we learn representations from two different datasets containing various degrees of abusive language. We compare the learned representation with two standard approaches; one based on lexica, and one based on data-specific $n$-grams. Our experiments show that learned representations \textit{do} contain useful information that can be used to improve detection performance when training data is limited."
}