Using combinations of different volumetric datasets is becoming more common in scientific applications, especially medical environments such as neurosurgery where multiple imaging...
Neural-symbolic systems are hybrid systems that integrate symbolic logic and neural networks. The goal of neural-symbolic integration is to benefit from the combination of feature...
This paper studies a text mining problem, comparative sentence mining. A comparative sentence expresses an ordering relation between two sets of entities with respect to some comm...
GOOD is a tailor-made, fully integrated publishing system that creates output documents for multiple media types used in both online and offline teaching modes at the University of...
Jacek Radajewski, Sally MacFarlane, Stijn Dekeyser
Statistical parsers trained and tested on the Penn Wall Street Journal (WSJ) treebank have shown vast improvements over the last 10 years. Much of this improvement, however, is ba...