@inproceedings{klang-nugues-2019-docria,
    title = "{D}ocria: Processing and Storing Linguistic Data with {W}ikipedia",
    author = "Klang, Marcus  and
      Nugues, Pierre",
    editor = "Hartmann, Mareike  and
      Plank, Barbara",
    booktitle = "Proceedings of the 22nd Nordic Conference on Computational Linguistics",
    month = sep # "–" # oct,
    year = "2019",
    address = "Turku, Finland",
    publisher = {Link{\"o}ping University Electronic Press},
    url = "https://preview.aclanthology.org/ingest_wac_2008/W19-6148/",
    pages = "400--405",
    abstract = "The availability of user-generated content has increased significantly over time. Wikipedia is one example of a corpora which spans a huge range of topics and is freely available. Storing and processing these corpora requires flexible documents models as they may contain malicious and incorrect data. Docria is a library which attempts to address this issue by providing a solution which can be used with small to large corpora, from laptops using Python interactively in a Jupyter notebook to clusters running map-reduce frameworks with optimized compiled code. Docria is available as open-source code."
}