We present a novel approach for learning patterns (sub-images) shared by multiple images without prior knowledge about the number and the positions of the patterns in the images. ...
We introduce a novel approach to the smart execution of scenario-based models of reactive systems, such as those resulting from the multi-modal inter-object language of live sequen...
Even in a massive corpus such as the Web, a substantial fraction of extractions appear infrequently. This paper shows how to assess the correctness of sparse extractions by utiliz...
We investigate the problem of learning document classifiers in a multilingual setting, from collections where labels are only partially available. We address this problem in the ...
Though overriding as a single and default mode of inheritance is adequate for most knowledge bases, a large class of applications naturally requires several inheritance modes and ...