@inproceedings{kreutz-daelemans-2018-exploring,
    title = "Exploring Classifier Combinations for Language Variety Identification",
    author = "Kreutz, Tim  and
      Daelemans, Walter",
    editor = {Zampieri, Marcos  and
      Nakov, Preslav  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Tiedemann, J{\"o}rg  and
      Malmasi, Shervin  and
      Ali, Ahmed},
    booktitle = "Proceedings of the Fifth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial 2018)",
    month = aug,
    year = "2018",
    address = "Santa Fe, New Mexico, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W18-3922/",
    pages = "191--198",
    abstract = "This paper describes CLiPS{'}s submissions for the Discriminating between Dutch and Flemish in Subtitles (DFS) shared task at VarDial 2018. We explore different ways to combine classifiers trained on different feature groups. Our best system uses two Linear SVM classifiers; one trained on lexical features (word n-grams) and one trained on syntactic features (PoS n-grams). The final prediction for a document to be in Flemish Dutch or Netherlandic Dutch is made by the classifier that outputs the highest probability for one of the two labels. This confidence vote approach outperforms a meta-classifier on the development data and on the test data."
}