Recent research has demonstrated the strong performance of hidden Markov models applied to information extraction--the task of populating database slots with corresponding phrases...
Mixed-initiativesystemspresent the challengeof finding an effective level of interaction betweenhumans and computers. Machinelearning presents a promising approachto this problemi...
One of the most important problems for an intelligent tutoring system is deciding how to respond when a student asks for help. Responding cooperatively requires an understanding o...
Wedescribe somenewpreprocessing techniques that enable faster domain-independentplanning. Thefirst set of techniquesis aimedat inferring state constraints from the structure of pl...
In problem solving, it is often important not only to find a solution but also to be able to explain it. We use the game of Bridge to illustrate how tactics, which formalise domai...
Automatedreasoning or theorem proving essentially amounts to solving search problems. Despite significant progress in recent years theorem provers still have manyshortcomings. The...
This paperconsidersthe problem of representingcomplex systems that evolve stochastically over time. Dynamic Bayesian networks provide a compact representation for stochastic proce...