We consider a setting for discriminative semisupervised learning where unlabeled data are used with a generative model to learn effective feature representations for discriminativ...
In this poster we propose a granular approach for presenting web search results. Sentences, taken from the top documents, are used as fine-grained representations of document cont...
Multi-class binary symbol classification requires the use of rich descriptors and robust classifiers. Shape representation is a difficult task because of several symbol distortions...
This paper introduces a technique for viewing text objects under changing size constraints in 2D environments. Our approach automatically combines font size reduction and content ...
Lance Good, Mark Stefik, Patrick Baudisch, Benjami...
This paper presents new classes of tree automata combining automata with equality test and automata modulo equational theories. We believe that these classes have a good potential ...