@inproceedings{jakubicek-etal-2020-current,
    title = "Current Challenges in Web Corpus Building",
    author = "Jakub{\'\i}{\v{c}}ek, Milo{\v{s}}  and
      Kov{\'a}{\v{r}}, Vojt{\v{e}}ch  and
      Rychl{\'y}, Pavel  and
      Suchomel, Vit",
    booktitle = "Proceedings of the 12th Web as Corpus Workshop",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2020.wac-1.1",
    pages = "1--4",
    abstract = "In this paper we discuss some of the current challenges in web corpus building that we faced in the recent years when expanding the corpora in Sketch Engine. The purpose of the paper is to provide an overview and raise discussion on possible solutions, rather than bringing ready solutions to the readers. For every issue we try to assess its severity and briefly discuss possible mitigation options.",
    language = "English",
    ISBN = "979-10-95546-68-9",
}