@inproceedings{virk-etal-2020-dream,
    title = "The {DR}ea{M} Corpus: A Multilingual Annotated Corpus of Grammars for the World`s Languages",
    author = {Virk, Shafqat Mumtaz  and
      Hammarstr{\"o}m, Harald  and
      Forsberg, Markus  and
      Wichmann, S{\o}ren},
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2020.lrec-1.110/",
    pages = "878--884",
    language = "eng",
    ISBN = "979-10-95546-34-4",
    abstract = "There exist as many as 7000 natural languages in the world, and a huge number of documents describing those languages have been produced over the years. Most of those documents are in paper format. Any attempts to use modern computational techniques and tools to process those documents will require them to be digitized first. In this paper, we report a multilingual digitized version of thousands of such documents searchable through some well-established corpus infrastructures. The corpus is annotated with various meta, word, and text level attributes to make searching and analysis easier and more useful."
}