PAC generalization bounds for co-training

Advances in Neural Information Processing Systems

Volumn , Issue , 2002, Pages

  Dasgupta, Sanjoy ^a   Littman, Michael L ^a   McAllester, David ^a  

^a AT AND T LABS RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CO-TRAINING; CO-TRAINING ALGORITHM; GENERALIZATION BOUND; GENERALIZATION ERROR; OBJECTIVE FUNCTIONS; RULE BASED; UNLABELED DATA;

EID: 84899008485     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. Blum, A. & Mitchell, T. (1998) Combining labeled and unlabeled data with co-training. COLT.
2. Collins, M. & Singer, Y. (1999) Unsupervised models for named entity classification. EMNLP.
3. Cover, T. & Thomas, J. (1991) Elements of information theory. Wiley.
4. Dempster, A., Laird, N. & Rubin, D. (1977) Maximum-likelihood from incomplete data via the EM algorithm. J. Royal Statist. Soc. Ser. B, 39:1-38.
5. Nigam, K. & Ghani, R. (2000) Analyzing the effectiveness and applicability of co-training. CIKM.
6. Yarowsky, D. (1995) Unsupervised word sense disambiguation rivaling supervised methods. ACL.