Text Classification from Labeled and Unlabeled Documents using EM Export

@article{citeulike:1139248, abstract = {This paper shows that the accuracy of learned text classifiers can be improved by augmenting a small number of labeled training documents with a large pool of unlabeled documents. This is important because in many text classification problems obtaining training labels is expensive, while large quantities of unlabeled documents are readily available.}, author = {Nigam, Kamal and Mccallum, Andrew K. and Thrun, Sebastian and Mitchell, Tom}, citeulike-article-id = {1139248}, citeulike-linkout-0 = {http://dx.doi.org/10.1023/A:1007692713085}, citeulike-linkout-1 = {http://www.springerlink.com/content/p4324q3673265225}, day = {1}, doi = {10.1023/A:1007692713085}, journal = {Machine Learning}, keywords = {text\_classification}, month = {May}, number = {2}, pages = {103--134}, posted-at = {2009-07-21 04:00:21}, priority = {2}, title = {Text Classification from Labeled and Unlabeled Documents using EM}, url = {http://dx.doi.org/10.1023/A:1007692713085}, volume = {39}, year = {2000} }

TY - JOUR ID - citeulike:1139248 L3 - citeulike-article-id:1139248 N2 - This paper shows that the accuracy of learned text classifiers can be improved by augmenting a small number of labeled training documents with a large pool of unlabeled documents. This is important because in many text classification problems obtaining training labels is expensive, while large quantities of unlabeled documents are readily available. IS - 2 JF - Machine Learning EP - 134 TI - Text Classification from Labeled and Unlabeled Documents using EM VL - 39 SP - 103 KW - text_classification AU - Nigam, Kamal AU - Mccallum, Andrew AU - Thrun, Sebastian AU - Mitchell, Tom PY - 2000/05/01/ UR - http://dx.doi.org/10.1023/A:1007692713085 ER -