@article{Lew04, author = {Lewis, D. D. and Yang, Y. and Rose, T. G. and Li, F.}, interhash = {ff940c50e028cb53fc10f99ddd39fe3e}, intrahash = {0db455903d09c97f4f6ccbfb95c66f9e}, journal = {Journal of Machine Learning Research}, number = {Apr}, pages = {361--397}, title = {RCV1: A New Benchmark Collection for Text Categorization Research}, url = {http://www.jmlr.org/papers/volume5/lewis04a/lewis04a.pdf}, volume = 5, year = 2004 } @article{rose2002rcv, author = {Rose, T.G. and Stevenson, M. and Whitehead, M.}, interhash = {3a817ba1a6c5e81efa0acc7faaa790ad}, intrahash = {b88233fe20a4454a2af000ad260166e7}, journal = {Proceedings of the Third International Conference on Language Resources and Evaluation}, pages = {29--31}, title = {{The reuters corpus volume 1-from yesterday’s news to tomorrow’s language resources}}, url = {http://about.reuters.com/researchandstandards/corpus/LREC_camera_ready.pdf}, year = 2002 }