@inproceedings{janssen-2016-teitok,
    title = "{TEITOK}: Text-Faithful Annotated Corpora",
    author = "Janssen, Maarten",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Grobelnik, Marko  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, Helene  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
    month = may,
    year = "2016",
    address = "Portoro{\v{z}}, Slovenia",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/landing_page/L16-1637/",
    pages = "4037--4043",
    abstract = "TEITOK is a web-based framework for corpus creation, annotation, and distribution, that combines textual and linguistic annotation within a single TEI based XML document. TEITOK provides several built-in NLP tools to automatically (pre)process texts, and is highly customizable. It features multiple orthographic transcription layers, and a wide range of user-defined token-based annotations. For searching, TEITOK interfaces with a local CQP server. TEITOK can handle various types of additional resources including Facsimile images and linked audio files, making it possible to have a combined written/spoken corpus. It also has additional modules for PSDX syntactic annotation and several types of stand-off annotation."
}