@inproceedings{barbaresi-2017-discriminating,
    title = "Discriminating between Similar Languages using Weighted Subword Features",
    author = "Barbaresi, Adrien",
    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/W17-1223/",
    doi = "10.18653/v1/W17-1223",
    pages = "184--189",
    abstract = "The present contribution revolves around a contrastive subword n-gram model which has been tested in the Discriminating between Similar Languages shared task. I present and discuss the method used in this 14-way language identification task comprising varieties of 6 main language groups. It features the following characteristics: (1) the preprocessing and conversion of a collection of documents to sparse features; (2) weighted character n-gram profiles; (3) a multinomial Bayesian classifier. Meaningful bag-of-n-grams features can be used as a system in a straightforward way, my approach outperforms most of the systems used in the DSL shared task (3rd rank)."
}