@inproceedings{oostdijk-boves-2004-using,
    title = "Using Large Multi-purpose Corpora for Specific Research Questions: Discourse Phenomena Related to Wh-questions in the Spoken {D}utch Corpus",
    author = "Oostdijk, Nelleke  and
      Boves, Lou",
    editor = "Lino, Maria Teresa  and
      Xavier, Maria Francisca  and
      Ferreira, F{\'a}tima  and
      Costa, Rute  and
      Silva, Raquel",
    booktitle = "Proceedings of the Fourth International Conference on Language Resources and Evaluation ({LREC}{'}04)",
    month = may,
    year = "2004",
    address = "Lisbon, Portugal",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/fix-sig-urls/L04-1265/",
    abstract = "In this paper, we investigate whether a dataset derived from a multi-purpose corpus such as the Spoken Dutch Corpus may be considered appropriate for developing a taxonomy of wh-questions, and a model of the way in which these questions are integrated in spoken discourse. We compare the results obtained from the Spoken Dutch Corpus with a similar analysis of a large random collection of FAQs from the internet. We find substantial differences between the questions in spoken discourse and FAQs. Therefore, it may not be trivial to use a general purpose corpus as a starting point for developing models for human-computer interaction."
}