@article{wikipediaxml:2005,
  author = {Denoyer, Ludovic and Gallinari, Patrick},
  title = {The Wikipedia XML Corpus},
  journal = {SIGIR Forum},
  year = {2006},
  url = {http://www-connex.lip6.fr/~denoyer/wikipediaXML/}
}

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

@inproceedings{halevymadhavan2003,
  author = {Halevy, Alon Y. and Madhavan, Jayant},
  title = {Corpus-Based Knowledge Representation},
  booktitle = {IJCAI-03, Proceedings of the Eighteenth International Joint Conference

             on Artificial Intelligence, Acapulco, Mexico, August 9-15, 2003},
  publisher = {Morgan Kaufmann},
  year = {2003},
  pages = {1567-1572}
}

@article{jiang97semantic,
  author = {Jiang, Jay J. and Conrath, David W.},
  title = {Semantic similarity based on corpus statistics and lexical taxonomy},
  journal = {CoRR},
  year = {1997},
  volume = {cmp-lg/9709008}
}