@inproceedings{hu-etal-2019-ensemble,
    title = "Ensemble Methods to Distinguish Mainland and {T}aiwan {C}hinese",
    author = "Hu, Hai  and
      Li, Wen  and
      Zhou, He  and
      Tian, Zuoyu  and
      Zhang, Yiwen  and
      Zou, Liang",
    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/jlcl-multiple-ingestion/W19-1417/",
    doi = "10.18653/v1/W19-1417",
    pages = "165--171",
    abstract = "This paper describes the IUCL system at VarDial 2019 evaluation campaign for the task of discriminating between Mainland and Taiwan variation of mandarin Chinese. We first build several base classifiers, including a Naive Bayes classifier with word n-gram as features, SVMs with both character and syntactic features, and neural networks with pre-trained character/word embeddings. Then we adopt ensemble methods to combine output from base classifiers to make final predictions. Our ensemble models achieve the highest F1 score (0.893) in simplified Chinese track and the second highest (0.901) in traditional Chinese track. Our results demonstrate the effectiveness and robustness of the ensemble methods."
}