@article{wikipediaxml:2005,
        title = {{T}he {W}ikipedia {X}{M}{L} {C}orpus},
        author = {Ludovic Denoyer and Patrick Gallinari},
        journal = {SIGIR Forum},
        year = 2006,
        url = {http://www-connex.lip6.fr/~denoyer/wikipediaXML/},
        description = {Wikipedia XML Corpus},
	biburl = {http://www.bibsonomy.org/bibtex/2493b849942fcaf9ba8e8e68e3cb46d38/hotho},
	keywords = {mining corpus wikipedia dm data xml ml}
}

@article{Lew04,
        title = {RCV1: A New Benchmark Collection for Text Categorization Research},
        author = {D. D. Lewis and Y. Yang and T. G. Rose and F. Li},
        journal = {Journal of Machine Learning Research},
        number = {Apr},
        pages = {361--397},
        volume = 5,
        year = 2004,
        url = {http://www.jmlr.org/papers/volume5/lewis04a/lewis04a.pdf},
        biburl = {http://www.bibsonomy.org/bibtex/20db455903d09c97f4f6ccbfb95c66f9e/hotho},
	keywords = {text corpus benchmark reuters classification RCV1}
}

@inproceedings{halevymadhavan2003,
        title = {Corpus-Based Knowledge Representation},
        author = {Alon Y. Halevy and Jayant Madhavan},
        booktitle = {IJCAI-03, Proceedings of the Eighteenth International Joint Conference
               on Artificial Intelligence, Acapulco, Mexico, August 9-15, 2003},
        editor = {Georg Gottlob and Toby Walsh},
        pages = {1567-1572},
        publisher = {Morgan Kaufmann},
        year = 2003,
        bibsource = {DBLP, http://dblp.uni-trier.de},
	biburl = {http://www.bibsonomy.org/bibtex/275d3c0fdd9fdbbfebd93cfda1ee42d28/hotho},
	keywords = {corpus knowledge representation based}
}