@inproceedings{swamy-etal-2019-studying,
    title = "Studying Generalisability across Abusive Language Detection Datasets",
    author = {Swamy, Steve Durairaj  and
      Jamatia, Anupam  and
      Gamb{\"a}ck, Bj{\"o}rn},
    editor = "Bansal, Mohit  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/K19-1088/",
    doi = "10.18653/v1/K19-1088",
    pages = "940--950",
    abstract = "Work on Abusive Language Detection has tackled a wide range of subtasks and domains. As a result of this, there exists a great deal of redundancy and non-generalisability between datasets. Through experiments on cross-dataset training and testing, the paper reveals that the preconceived notion of including more non-abusive samples in a dataset (to emulate reality) may have a detrimental effect on the generalisability of a model trained on that data. Hence a hierarchical annotation model is utilised here to reveal redundancies in existing datasets and to help reduce redundancy in future efforts."
}