- view fewer
(Proceedings) Kernel Methods for Document Filtering.
Department of Commerce, National Institute of Standards and Technology
This paper describes the algorithms inplemented 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
|Event:||Kernel Methods for Document Filtering|
|Keywords:||computation learning theory, information filtering, KerMIT, Kernel Methods, margin-based algorithms, routing tasks, support vector, SVM|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only