@inproceedings{bestgen-2017-improving,
    title = "Improving the Character Ngram Model for the {DSL} Task with {BM}25 Weighting and Less Frequently Used Feature Sets",
    author = "Bestgen, Yves",
    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/W17-1214/",
    doi = "10.18653/v1/W17-1214",
    pages = "115--123",
    abstract = "This paper describes the system developed by the Centre for English Corpus Linguistics (CECL) to discriminating similar languages, language varieties and dialects. Based on a SVM with character and POStag n-grams as features and the BM25 weighting scheme, it achieved 92.7{\%} accuracy in the Discriminating between Similar Languages (DSL) task, ranking first among eleven systems but with a lead over the next three teams of only 0.2{\%}. A simpler version of the system ranked second in the German Dialect Identification (GDI) task thanks to several ad hoc postprocessing steps. Complementary analyses carried out by a cross-validation procedure suggest that the BM25 weighting scheme could be competitive in this type of tasks, at least in comparison with the sublinear TF-IDF. POStag n-grams also improved the system performance."
}