@InProceedings{li-wang:2017:I17-2,
  author    = {Li, Changliang  and  Wang, Xiuying},
  title     = {Building Large Chinese Corpus for Spoken Dialogue Research in Specific Domains},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {320--324},
  abstract  = {Corpus is a valuable resource for information retrieval and data-driven
	natural language processing systems,especially for spoken dialogue research in
	specific domains. However,there is little non-English corpora, particular for
	ones in Chinese. Spoken by the nation with the largest population
	in  the  world,  Chinese  become increasingly prevalent and popular
	among millions of people worldwide. In this paper, we build a large-scale
	and high-quality Chinese corpus, called CSDC (Chinese Spoken Dialogue Corpus).
	It contains five domains and more than 140 thousand dialogues in all. Each
	sentence in this corpus is annotated with slot information additionally
	compared to other corpora. To our best knowledge, this is the largest Chinese
	spoken dialogue corpus, as well as the first one with slot information. With
	this corpus, we proposed a method and did a well-designed experiment. The
	indicative result is reported at last.},
  url       = {http://www.aclweb.org/anthology/I17-2054}
}