@inproceedings{hayes90construe,
        title = {{CONSTRUE/TIS}: A System for Content-Based Indexing of a Database of News Stories},
        author = {Philip J. Hayes and Steven P. Weinstein},
        booktitle = {Proceedings of the 2nd Conference on Innovative Applications of Artificial Intelligence (IAAI-90), May 1-3, 1990, Washington, DC, USA},
        editor = {Alain T. Rappaport and Reid G. Smith},
        pages = {49--64},
        publisher = {AAAI Press, Chicago, IL, USA},
        year = 1991,
        url = {http://portal.acm.org/citation.cfm?id=653070},
        isbn = {0-262-68068-8},
	description = {CONSTRUE/TIS},
	biburl = {http://www.bibsonomy.org/bibtex/2ec2e67014f388f083f662c4c6d09f7e5/sb3000},
	keywords = {reuters corpus text-classification}
}

@book{kucera67analysis,
        title = {Computational Analysis of Present-Day {A}merican {E}nglish},
        address = {Providence, RI, USA},
        author = {Henry Kucera and W. Nelson Francis},
        publisher = {Brown University Press},
        year = 1967,
        biburl = {http://www.bibsonomy.org/bibtex/284e01f88594cbc1f6bd136fcbeaeb80b/sb3000},
	keywords = {text-mining corpus linguistics}
}

@article{debole05reutersanalysis,
        title = {An Analysis of the Relative Hardness of {R}euters-21578 Subsets},
        author = {Franca Debole and Fabrizio Sebastiani},
        journal = {Journal of the American Society for Information Science and},
        number = 6,
        pages = {584--596},
        volume = 56,
        year = 2004,
        url = {http://faure.isti.cnr.it/~fabrizio/Publications/JASIST05.pdf},
        biburl = {http://www.bibsonomy.org/bibtex/22d769d6047b7618cb13769ea2b2255df/sb3000},
	keywords = {text-classification corpus reuters-21578}
}

@techreport{francis79browncorpus,
        title = {Brown Corpus Manual},
        author = {W. N. Francis and H. Kucera},
        institution = {Department of Linguistics, Brown University, Providence, Rhode Island, US},
        year = 1979,
        url = {http://icame.uib.no/brown/bcm.html},
        biburl = {http://www.bibsonomy.org/bibtex/260bb0c74c2ecced0632393e47eb64f48/sb3000},
	keywords = {linguistics corpus text-mining}
}

@article{apte94reuters,
        title = {Automated learning of decision rules for text categorization},
        address = {New York, NY, USA},
        author = {Chidanand Apt\'{e} and Fred Damerau and Sholom M. Weiss},
        journal = {ACM Transactions on Information Systems},
        number = 3,
        pages = {233--251},
        publisher = {ACM},
        volume = 12,
        year = 1994,
        url = {http://portal.acm.org/citation.cfm?id=183422.183423},
        issn = {1046-8188},
	doi = {http://doi.acm.org/10.1145/183422.183423},
	biburl = {http://www.bibsonomy.org/bibtex/23d97cb3619061688b76da442aa7689c0/sb3000},
	keywords = {corpus reuters text-classification}
}

@inproceedings{hersh94ohsu,
        title = {Ohsumed: An {I}nteractive {R}etrieval {E}vealuation and new large {T}est {C}ollection for {R}esearch},
        author = {W. R. Hersh and C. Buckley and T. J. Leone and D. H. Hickam},
        booktitle = {{Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval}},
        publisher = {ACM Press},
        year = 1994,
        biburl = {http://www.bibsonomy.org/bibtex/2dcf4f4f5693a73b551b93e7e31ce11a3/sb3000},
	keywords = {corpus text-mining}
}