Abstract
Since 1998 there has been significant interest in supervised learning algorithms that combine labeled and unlabeled data for text learning tasks. The co-training algorithm applied to datasets which have a natural separation of their features into two disjoint sets. In this paper, we demonstrate that when learning from labeled and unlabeled data using co-training algorithm, selecting those document examples first which have two parts of best matching features can obtain a good performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Nigam, K., McCallum, A., Thrun, S., Mitchell, T.: Text classification from labeled and unlabeled documents using EM. Machine Learning 39(2/3), 103–134 (2000)
Jaakkola, T., Haussler, D.: Exploiting generative models in discriminative classifiers. In: Advances in NIPS 11 (1999)
Joachims, T.: Transductive inference for text classification using support vector machines. In: Proceedings of ICML 1999 (1999)
Blum, A., Mitchell, T.M.: Combining labeled and unlabeled data with co-training. In: COLT 1998, Madison, WI, USA,
Nigam, K., Ghani, R.: Analyzing the effectiveness and applicability of co-training. In: 9th International Conference on Information and Knowledge Management (CIKM), 2000. Computational Learning Theory, pp. 92–100 (1998), www.cs.cmu.edu/knigam
Lewis, D.D.: Naive (Bayes) at forty: The independence assumption in information retrieval. In: Nédellec, C., Rouveirol, C. (eds.) Machine Learning: ECML-98. LNCS, vol. 1398, Springer, Heidelberg (1998)
McCallum, A., Nigam, K.: A comparison of event models for naive Bayes text classification. In: AAAI-98 Workshop on Learning for Text Categorization, Tech. rep. WS-98-05, AAAI Press (1998), http://www.cs.cmu.edu/mccallum
Sebastiani, F.: Machine learning in automated text categorization. ACM Computing Surveys 34(1), 1–47 (2002)
Yang, Y., Liu, X.: A re-examination of Text Categorization Methods. In: SIGIR-99
Liu, B., Dai, Y., Li, X., Lee, W.S., Yu, P.S.: Building text classifiers using positive and unlabeled examples. In: Proc. of the 3rd IEEE Int’l Conf. on Data Mining. Melbourne (ICDM-03), pp. 179–188. IEEE Computer Society, Los Alamitos (2003)
Denis, F.: PAC learning from positive statistical queries. In: Proc. 9th International Conference on Algorithmic Learning Theory-ALT 987, pp. 112–126 (1998)
Liu, B., Lee, W.S., Yu, P., Li, X.: Partially supervised classification of text documents. In: ICML-02
Shih, L.K., Karger, D.R.: Using URLs and table layout for Web classification tasks. In: Feldman, S., Uretsky, M., Najork, M., Wills, C.E. (eds.) Proc. of the 13th Int’l Conf. on the World Wide Web (WWW-2004), pp. 193–202. ACM Press, New York (2004)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B 39(1), 1–38 (1977)
Brualdi, R.A.: Introductory Combinatorics, 3rd edn., pp. 200–300. Prentice Hall Inc, Englewood Cliffs (1999)
Keerthi, S.S., Shevade, S.K., Bhattacharyya, C., Murthy, K.R.K.: Improvements to Platt’s SMO Algorithm for SVM Classifier Design. Neural Computation 13(3), 637–649
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, H., Ji, L., Zuo, W. (2007). Best-Match Method Used in Co-training Algorithm. In: Washio, T., et al. Emerging Technologies in Knowledge Discovery and Data Mining. PAKDD 2007. Lecture Notes in Computer Science(), vol 4819. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77018-3_40
Download citation
DOI: https://doi.org/10.1007/978-3-540-77018-3_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77016-9
Online ISBN: 978-3-540-77018-3
eBook Packages: Computer ScienceComputer Science (R0)