@article{lui-etal-2014-automatic,
    title = "Automatic Detection and Language Identification of Multilingual Documents",
    author = "Lui, Marco  and
      Lau, Jey Han  and
      Baldwin, Timothy",
    editor = "Lin, Dekang  and
      Collins, Michael  and
      Lee, Lillian",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "2",
    year = "2014",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/Q14-1003/",
    doi = "10.1162/tacl_a_00163",
    pages = "27--40",
    abstract = "Language identification is the task of automatically detecting the language(s) present in a document based on the content of the document. In this work, we address the problem of detecting documents that contain text from more than one language (multilingual documents). We introduce a method that is able to detect that a document is multilingual, identify the languages present, and estimate their relative proportions. We demonstrate the effectiveness of our method over synthetic data, as well as real-world multilingual documents collected from the web."
}