We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
Abstract. In Machine Learning, ensembles are combination of classifiers. Their objective is to improve the accuracy. In previous works, we have presented a method for the generati...
Hypertext is a technology well-suited to exploring different kinds of representational problems. It can be used first as an informal mechanism to describe the attributes of object...
Motion segmentation is a classic and on-going research topic which is an important pre-stage for many video processes. The reliability of the motion field calculation directly dete...
The idea of representing images using a bag of visual words is currently popular in object category recognition. Since this representation is typically constructed using unsupervi...