@inproceedings{gamallo-etal-2017-perplexity,
    title = "A Perplexity-Based Method for Similar Languages Discrimination",
    author = "Gamallo, Pablo  and
      Pichel, Jose Ramom  and
      Alegria, I{\~n}aki",
    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/add-emnlp-2024-awards/W17-1213/",
    doi = "10.18653/v1/W17-1213",
    pages = "109--114",
    abstract = "This article describes the system submitted by the Citius{\_}Ixa{\_}Imaxin team to the VarDial 2017 (DSL and GDI tasks). The strategy underlying our system is based on a language distance computed by means of model perplexity. The best model configuration we have tested is a voting system making use of several $n$-grams models of both words and characters, even if word unigrams turned out to be a very competitive model with reasonable results in the tasks we have participated. An error analysis has been performed in which we identified many test examples with no linguistic evidences to distinguish among the variants."
}