@inproceedings{fankhauser-etal-2020-evaluating,
    title = "Evaluating a Dependency Parser on {D}e{R}e{K}o",
    author = "Fankhauser, Peter  and
      Do, Bich-Ngoc  and
      Kupietz, Marc",
    editor = {Ba{\'n}ski, Piotr  and
      Barbaresi, Adrien  and
      Clematide, Simon  and
      Kupietz, Marc  and
      L{\"u}ngen, Harald  and
      Pisetta, Ines},
    booktitle = "Proceedings of the 8th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Ressources Association",
    url = "https://aclanthology.org/2020.cmlc-1.2",
    pages = "10--14",
    abstract = "We evaluate a graph-based dependency parser on DeReKo, a large corpus of contemporary German. The dependency parser is trained on the German dataset from the SPMRL 2014 Shared Task which contains text from the news domain, whereas DeReKo also covers other domains including fiction, science, and technology. To avoid the need for costly manual annotation of the corpus, we use the parser{'}s probability estimates for unlabeled and labeled attachment as main evaluation criterion. We show that these probability estimates are highly correlated with the actual attachment scores on a manually annotated test set. On this basis, we compare estimated parsing scores for the individual domains in DeReKo, and show that the scores decrease with increasing distance of a domain to the training corpus.",
    language = "English",
    ISBN = "979-10-95546-61-0",
}