We describe a novel approach to unsupervised learning of the events that make up a script, along with constraints on their temporal ordering. We collect naturallanguage descriptio...
Michaela Regneri, Alexander Koller, Manfred Pinkal
maintain awareness of its environment for a long period of time. Additionally, knowledge-intensive agents must be engineered such that their knowledge can be easily updated as envi...
Abstract 1 Different definitions of agents use concepts such as autonomy, pro-activity, reactivity, social abilities, and intentional models. Very few (if any), however, refer to...
Frances M. T. Brazier, Maarten van Steen, Niek J. ...
The three-tiered discourse representation defined in (Luperfoy, 1991) is applied to multimodal humancomputer interface (HCI) dialogues. In the applied system the three tiers are (...
This paper describes an algorithm, called CQ-learning, which learns to adapt the state representation for multi-agent systems in order to coordinate with other agents. We propose ...