@inproceedings{malmasi-zampieri-2017-german,
    title = "{G}erman Dialect Identification in Interview Transcriptions",
    author = "Malmasi, Shervin  and
      Zampieri, Marcos",
    editor = {Nakov, Preslav  and
      Zampieri, Marcos  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Tiedemann, J{\"o}rg  and
      Malmasi, Shevin  and
      Ali, Ahmed},
    booktitle = "Proceedings of the Fourth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial)",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W17-1220/",
    doi = "10.18653/v1/W17-1220",
    pages = "164--169",
    abstract = "This paper presents three systems submitted to the German Dialect Identification (GDI) task at the VarDial Evaluation Campaign 2017. The task consists of training models to identify the dialect of Swiss-German speech transcripts. The dialects included in the GDI dataset are Basel, Bern, Lucerne, and Zurich. The three systems we submitted are based on: a plurality ensemble, a mean probability ensemble, and a meta-classifier trained on character and word n-grams. The best results were obtained by the meta-classifier achieving 68.1{\%} accuracy and 66.2{\%} F1-score, ranking first among the 10 teams which participated in the GDI shared task."
}