Combining Labeled and Unlabeled Data with Co-training

@inproceedings{blum:mitchell, abstract = {We consider the problem of using a large unlabeled sample to boost performance of a learning algorithm when only a small set of labeled examples is available. In particular, we consider a problem setting motivated by the task of learning to classify web pages, in which the description of each example can be partitioned into two distinct views. For example, the description of a web page can be partitioned into the words occurring on that page, and the words occurring in hyperlinks that point to...}, author = {Blum, Avrim and Mitchell, Tom }, booktitle = {COLT: Proceedings of the Workshop on Computational Learning Theory, Morgan Kaufmann Publishers}, citeulike-article-id = {140030}, keywords = {blum, co-training, mitchell}, posted-at = {2005-10-09 12:59:01}, priority = {5}, title = {Combining Labeled and Unlabeled Data with Co-training}, url = {http://citeseer.ist.psu.edu/blum98combining.html}, year = {1998} }

TY - CONF ID - blum:mitchell L3 - citeulike-article-id:140030 N2 - We consider the problem of using a large unlabeled sample to boost performance of a learning algorithm when only a small set of labeled examples is available. In particular, we consider a problem setting motivated by the task of learning to classify web pages, in which the description of each example can be partitioned into two distinct views. For example, the description of a web page can be partitioned into the words occurring on that page, and the words occurring in hyperlinks that point to... TI - Combining Labeled and Unlabeled Data with Co-training T2 - COLT: Proceedings of the Workshop on Computational Learning Theory, Morgan Kaufmann Publishers KW - blum KW - co-training KW - mitchell AU - Blum, Avrim AU - Mitchell, Tom PY - 1998/// UR - http://citeseer.ist.psu.edu/blum98combining.html ER -