A general model is proposed for studying ranking problems. We investigate learning methods based on empirical minimization of the natural estimates of the ranking risk. The empiric...
Class binarizations are effective methods for improving weak learners by decomposing multi-class problems into several two-class problems. This paper analyzes how these methods can...
This work proposes a new approach to the retrieval of images from text queries. Contrasting with previous work, this method relies on a discriminative model: the parameters are sel...
Abstract. Most classification methods assume that the samples are drawn independently and identically from an unknown data generating distribution, yet this assumption is violated ...
This paper presents a method of automatically constructing information extraction patterns on predicate-argument structures (PASs) obtained by full parsing from a smaller training...