@inproceedings{jauhiainen-etal-2019-discriminating,
    title = "Discriminating between {M}andarin {C}hinese and {S}wiss-{G}erman varieties using adaptive language models",
    author = "Jauhiainen, Tommi  and
      Lind{\'e}n, Krister  and
      Jauhiainen, Heidi",
    editor = {Zampieri, Marcos  and
      Nakov, Preslav  and
      Malmasi, Shervin  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Tiedemann, J{\"o}rg  and
      Ali, Ahmed},
    booktitle = "Proceedings of the Sixth Workshop on {NLP} for Similar Languages, Varieties and Dialects",
    month = jun,
    year = "2019",
    address = "Ann Arbor, Michigan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W19-1419/",
    doi = "10.18653/v1/W19-1419",
    pages = "178--187",
    abstract = "This paper describes the language identification systems used by the SUKI team in the Discriminating between the Mainland and Taiwan variation of Mandarin Chinese (DMT) and the German Dialect Identification (GDI) shared tasks which were held as part of the third VarDial Evaluation Campaign. The DMT shared task included two separate tracks, one for the simplified Chinese script and one for the traditional Chinese script. We submitted three runs on both tracks of the DMT task as well as on the GDI task. We won the traditional Chinese track using Naive Bayes with language model adaptation, came second on GDI with an adaptive version of the HeLI 2.0 method, and third on the simplified Chinese track using again the adaptive Naive Bayes."
}