@inproceedings{vernetti-freitas-2020-assessment,
    title = "An Assessment of Language Identification Methods on Tweets and {W}ikipedia Articles",
    author = "Vernetti, Pedro  and
      Freitas, Larissa",
    editor = "Cunha, Rossana  and
      Shaikh, Samira  and
      Varis, Erika  and
      Georgi, Ryan  and
      Tsai, Alicia  and
      Anastasopoulos, Antonios  and
      Chandu, Khyathi Raghavi",
    booktitle = "Proceedings of the Fourth Widening Natural Language Processing Workshop",
    month = jul,
    year = "2020",
    address = "Seattle, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.winlp-1.15/",
    doi = "10.18653/v1/2020.winlp-1.15",
    pages = "58--60",
    abstract = "Language identification is the task of determining the language which a given text is written. This task is important for Natural Language Processing and Information Retrieval activities. Two popular approaches for language identification are the N-grams and stopwords models. In this paper, these two models were tested on different types of documents such as short, irregular texts (tweets) and long, regular texts (Wikipedia articles)."
}