High-performance semi-supervised learning using discriminatively constrained generative models

ICML 2010 - Proceedings, 27th International Conference on Machine Learning

Volumn , Issue , 2010, Pages 319-326

  Druck, Gregory ^a   Mccallum, Andrew ^a  

^a UNIVERSITY OF MASSACHUSETTS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADDITIONAL FLEXIBILITIES; COORDINATE ASCENT; GENERATIVE MODEL; HYBRID MODEL; LABELED DATA; LATENT STRUCTURES; LATENT VARIABLE; LOGLINEAR MODEL; ONE STEP; POSTERIOR DISTRIBUTIONS; PREDICTION TASKS; SEMI-SUPERVISED LEARNING; SEMI-SUPERVISED LEARNING METHODS; SEMI-SUPERVISED METHOD; SEQUENCE LABELING; SINGLE OBJECTIVE; STATIONARY POINTS; TEST TIME;

ALGORITHMS; REGRESSION ANALYSIS;

SUPERVISED LEARNING;

EID: 77956547444     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Ando, R. K. and Zhang, T. A high-performance semi-supervised learning method for text chunking. In Proc. of Meeting of Assoc. for Computational Linguistics, pp. 1-9, 2005.
2. Bellare, K., Druck, G., and McCallum, A. Alternating projections for learning with expectation constraints. In Proc. of Conf. on Uncertainty in Artificial Intelligence, 2009.
3. Chang, M., Ratinov, L. and Roth, D. Guiding semi-supervision with constraint-driven learning. In Proc. of Meeting of Assoc. for Computational Linguistics, pp. 280-287, 2007.
4. Cozman, F. and Cohen, I. Risks of semi-supervised learning: How unlabeled data can degrade performance of generative classifiers. In Semi-Supervised Learning. MIT Press, 2006.
5. Dempster, A. P., Laird, N. M., and Rubin, D. B. Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical SocietySer. B, 39(1):1-38, 1977.
6. Dudik, Miroslav. Maximum entropy density estimation and modeling geographic distributions of species. PhD thesis, Department of Computer Science, Princeton University, 2007.
7. Ganchev, K., Graça, J., Gillenwater, J. and Taskar, B. Posterior regularization for structured latent variable models. Technical Report MS-CIS-09-16, University of Pennsylvania Department of Computer and Information Science, 2009.
8. Grandvalet, Y. and Bengio, Y. Entropy regularization. In Semi-Supervised Learning. MIT Press, 2006.
9. Koo, T., Carreras, X., and Collins, M. Simple semi-supervised dependency parsing. In Proc. of Meeting of Assoc. for Computational Linguistics, pp. 595-603, 2008.
10. Lafferty, J., McCallum, A., and Pereira, F. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proc. Int'l. Conf. on Machine Learning, pp. 282-289, 2001.
11. Lasserre, J. A., Bishop, C. M., and Minka, T. P. Principled hybrids of generative and discriminative models. In Conf. on Computer Vision and Pattern Recognition, pp. 87-94, 2006.
12. Liang, P., Jordan, M. I. and Klein, D. Learning from measurements in exponential families. In Proc. Int'l. Conf. on Machine Learning, pp. 641-648, 2009.
13. Mann, G. and McCallum, A. Generalized expectation criteria for semi-supervised learning of conditional random fields. In Proc. of Meeting of Assoc. for Computational Linguistics, pp. 870-878, 2008.
14. McCallum, A., Pal, C, Druck, G. and Wang, X. Multi-conditional learning: Generative/discrimi-native training for clustering and classification. In Proc. Conf. on A.I., pp. 433-439, 2006. (Pubitemid 44705322)
15. Nigam, K., McCallum, A. and Mitchell, T. Semi-supervised text classification using em. In Semi-Supervised Learning. MIT Press, 2006.
16. Peng, F. and Mccallum, A. Accurate information extraction from research papers using conditional random fields. In Proc. of Human Language Technology Conf, pp. 329-336, 2004.
17. Quadrianto, N., Petterson, J., and Smola, A. Distribution matching for transduction. In Bengio, Y., Schuurmans, D., Lafferty, J., Williams, C. K. I., and Culotta, A. (eds.), Neural Information Processing Systems, pp. 1500-1508. MIT Press, 2009.
18. Suzuki, J. and Isozaki, H. Semi-supervised sequential labeling and segmentation using giga-word scale unlabeled data. In Proc. of Meeting of Assoc. for Computational Linguistics, pp. 665-673, 2008.