@inproceedings{aulamo-tiedemann-2019-opus,
    title = "The {OPUS} Resource Repository: An Open Package for Creating Parallel Corpora and Machine Translation Services",
    author = {Aulamo, Mikko  and
      Tiedemann, J{\"o}rg},
    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/landing_page/W19-6146/",
    pages = "389--394",
    abstract = "This paper presents a flexible and powerful system for creating parallel corpora and for running neural machine translation services. Our package provides a scalable data repository backend that offers transparent data pre-processing pipelines and automatic alignment procedures that facilitate the compilation of extensive parallel data sets from a variety of sources. Moreover, we develop a web-based interface that constitutes an intuitive frontend for end-users of the platform. The whole system can easily be distributed over virtual machines and implements a sophisticated permission system with secure connections and a flexible database for storing arbitrary metadata. Furthermore, we also provide an interface for neural machine translation that can run as a service on virtual machines, which also incorporates a connection to the data repository software."
}