@inproceedings{wisniewski-yvon-2019-bad,
    title = "{H}ow {B}ad are {P}o{S} {T}agger in {C}ross-{C}orpora {S}ettings? {E}valuating {A}nnotation {D}ivergence in the {UD} {P}roject.",
    author = "Wisniewski, Guillaume  and
      Yvon, Fran{\c{c}}ois",
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/N19-1019/",
    doi = "10.18653/v1/N19-1019",
    pages = "218--227",
    abstract = "The performance of Part-of-Speech tagging varies significantly across the treebanks of the Universal Dependencies project. This work points out that these variations may result from divergences between the annotation of train and test sets. We show how the annotation variation principle, introduced by Dickinson and Meurers (2003) to automatically detect errors in gold standard, can be used to identify inconsistencies between annotations; we also evaluate their impact on prediction performance."
}