@inproceedings{rosen-vavrin-2012-building,
    title = "Building a multilingual parallel corpus for human users",
    author = "Rosen, Alexandr  and
      Vav{\v{r}}{\'i}n, Martin",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Do{\u{g}}an, Mehmet U{\u{g}}ur  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
    month = may,
    year = "2012",
    address = "Istanbul, Turkey",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/ingest-emnlp/L12-1058/",
    pages = "2447--2452",
    abstract = "We present the architecture and the current state of InterCorp, a multilingual parallel corpus centered around Czech, intended primarily for human users and consisting of written texts with a focus on fiction. Following an outline of its recent development and a comparison with some other multilingual parallel corpora we give an overview of the data collection procedure that covers text selection criteria, data format, conversion, alignment, lemmatization and tagging. Finally, we show a sample query using the web-based search interface and discuss challenges and prospects of the project."
}