@inproceedings{tuggener-2017-method,
    title = "A method for in-depth comparative evaluation: How (dis)similar are outputs of pos taggers, dependency parsers and coreference resolvers really?",
    author = "Tuggener, Don",
    editor = "Lapata, Mirella  and
      Blunsom, Phil  and
      Koller, Alexander",
    booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/E17-1018/",
    pages = "188--198",
    abstract = "This paper proposes a generic method for the comparative evaluation of system outputs. The approach is able to quantify the pairwise differences between two outputs and to unravel in detail what the differences consist of. We apply our approach to three tasks in Computational Linguistics, i.e. POS tagging, dependency parsing, and coreference resolution. We find that system outputs are more distinct than the (often) small differences in evaluation scores seem to suggest."
}