@inproceedings{kovarik-2000-large,
    title = "How Should a Large Corpus Be Built?-A Comparative Study of Closure in Annotated Newspaper Corpora from Two {C}hinese Sources, Towards Building a Larger Representative Corpus Merged from Representative Sublanguage Collections",
    author = "Kovarik, John J.",
    booktitle = "Second {C}hinese Language Processing Workshop",
    month = oct,
    year = "2000",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/W00-1217/",
    doi = "10.3115/1117769.1117788",
    pages = "116--123"
}