@inproceedings{dunn-2019-modeling,
    title = "Modeling Global Syntactic Variation in {E}nglish Using Dialect Classification",
    author = "Dunn, Jonathan",
    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/fix-sig-urls/W19-1405/",
    doi = "10.18653/v1/W19-1405",
    pages = "42--53",
    abstract = "This paper evaluates global-scale dialect identification for 14 national varieties of English on both web-crawled data and Twitter data. The paper makes three main contributions: (i) introducing data-driven language mapping as a method for selecting the inventory of national varieties to include in the task; (ii) producing a large and dynamic set of syntactic features using grammar induction rather than focusing on a few hand-selected features such as function words; and (iii) comparing models across both web corpora and social media corpora in order to measure the robustness of syntactic variation across registers."
}