Support vector machine active learning with applications to text classification Export

@article{Tong2000svm-al-text, abstract = {Support vector machines have met with significant success in numerous real-world learning tasks. However, like most machine learning algorithms, they are generally applied using a randomly selected training set classified in advance. In many settings, we also have the option of using \<em\>pool-based active learning\</em\>. Instead of using a randomly selected training set, the learner has access to a pool of unlabeled instances and can request the labels for some number of them. We introduce a new algorithm for performing active learning with support vector machines, i.e., an algorithm for choosing which instances to request next. We provide a theoretical motivation for the algorithm using the notion of a \<em\>version space\</em\>. We present experimental results showing that employing our active learning method can significantly reduce the need for labeled training instances in both the standard inductive and transductive settings.}, address = {Cambridge, MA, USA}, author = {Tong, Simon and Koller, Daphne}, citeulike-article-id = {716139}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=944793}, citeulike-linkout-1 = {http://dx.doi.org/10.1023/A:1009715923555}, doi = {10.1023/A:1009715923555}, issn = {1532-4435}, journal = {J. Mach. Learn. Res.}, keywords = {active, classification, learning, machine, support, text, vector}, pages = {45--66}, posted-at = {2009-02-17 11:15:04}, priority = {2}, publisher = {JMLR.org}, title = {Support vector machine active learning with applications to text classification}, url = {http://dx.doi.org/10.1023/A:1009715923555}, volume = {2}, year = {2002} }

TY - JOUR ID - Tong2000svm-al-text L3 - citeulike-article-id:716139 N2 - Support vector machines have met with significant success in numerous real-world learning tasks. However, like most machine learning algorithms, they are generally applied using a randomly selected training set classified in advance. In many settings, we also have the option of using <em>pool-based active learning</em>. Instead of using a randomly selected training set, the learner has access to a pool of unlabeled instances and can request the labels for some number of them. We introduce a new algorithm for performing active learning with support vector machines, i.e., an algorithm for choosing which instances to request next. We provide a theoretical motivation for the algorithm using the notion of a <em>version space</em>. We present experimental results showing that employing our active learning method can significantly reduce the need for labeled training instances in both the standard inductive and transductive settings. JF - J. Mach. Learn. Res. SN - 1532-4435 AD - Cambridge, MA, USA EP - 66 TI - Support vector machine active learning with applications to text classification PB - JMLR.org VL - 2 SP - 45 KW - active KW - classification KW - learning KW - machine KW - support KW - text KW - vector AU - Tong, Simon AU - Koller, Daphne PY - 2002/// UR - http://dx.doi.org/10.1023/A:1009715923555 ER -