Kernel Methods for Document Filtering

This paper describes the algorithms implemented by the KerMIT consortium for its participation in the Trec 2002 Filtering track. The consortium submitted runs for the routing task using a linear SVM, for the batch task using the same SVM in combination with an innovation threshold-selection mechanism, and for the adaptive task using both a second-order perceptron and a combination of SVM and perceptron with uneven margin. Results seem to indicate that these algorithm performed relatively well on the extensive TREC benchmark.