Ranking with Unlabeled Data: A First Study
作者： Nicolas Usunier , Massih-Reza Amini , Tuong Vinh Truong , Patrick Gallinari
DOI:
关键词:
摘要: In this paper, we present a general learning framework which treats the ranking problem for various Information Retrieval tasks. We extend training set generalization error bound proposed by Matti Kaariannan to case and show that use of unlabeled data can be beneficial function. finally discuss open issues regarding during
archives-ouvertes.fr参考文章(5)
Massih R. Amini, Nicolas Usunier, Patrick Gallinari, Automatic text summarization based on word-clusters and ranking algorithms european conference on information retrieval. ,vol. 3408, pp. 142- 156 ,(2005) , 10.1007/978-3-540-31865-1_11
Matti Kääriäinen, Generalization error bounds using unlabeled data conference on learning theory. pp. 127- 142 ,(2005) , 10.1007/11503415_9
Yoav Freund, Raj Iyer, Robert E Schapire, Yoram Singer, An efficient boosting algorithm for combining preferences Journal of Machine Learning Research. ,vol. 4, pp. 933- 969 ,(2003) , 10.1162/1532443041827916
Ofer Dekel, Christopher D Manning, Yoram Singer, Log-Linear Models for Label Ranking neural information processing systems. ,vol. 16, pp. 497- 504 ,(2003)
Colin McDiarmid, Surveys in Combinatorics, 1989: On the method of bounded differences Cambridge University Press. pp. 148- 188 ,(1989) , 10.1017/CBO9781107359949.008