Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
Large corporations increasingly utilize business process models for documenting and redesigning their operations. The extent of such modeling initiatives with several hundred mode...
Stanford dependencies are widely used in natural language processing as a semanticallyoriented representation, commonly generated either by (i) converting the output of a constitu...
Traditional object-oriented programming languages can be difficult to use when working with ontologies, leading to the creation of domain-specific languages designed specifically...
Vangelis Vassiliadis, Jan Wielemaker, Chris Mungal...
— Our long-term objective is to develop robots that engage in natural language-mediated cooperative tasks with humans. To support this goal, we are developing an amodal represent...