Unrehearsed spoken language often contains disfluencies. In order to correctly interpret a spoken utterance, any such disfluencies must be identified and removed or otherwise deal...
Over the past years, the reengineering of legacy software systems to object oriented platforms has received significant attention. In this paper, we present a generic re-engineeri...
Although image understanding and natural language processing constitute two major areas of AI, they have mostly been studied independentlyof each other. Only a few attempts have b...
The well-known and very simple MinOver algorithm is reformulated for incremental support vector classification with and without kernels. A modified proof for its O(t-1/2 ) converge...
In this article we propose a method for parameter learning within the energy minimisation framework for segmentation. We do this in an incremental way where user input is required ...