Ubiquitous Knowledge Modeling for Dialogue Systems

The main general problem that we want to address is the reconfiguration of dialogue systems to work with a generic plug-and-play device. This paper describes our research in designing knowledge-based everyday devices that can be dynamically adapted to spoken dialogue systems. We propose a model for ubiquitous knowledge representation that enables the spoken dialogue system to be aware of the devices belonging to the domain and of the tasks they provide. We consider that each device can be augmented with computational capabilities in order to support its own knowledge model. A knowledge-based broker adapts the spoken dialogue system to deal with an arbitrary set of devices. The knowledge integration process between the knowledge models of the devices and the knowledge model of the broker is depicted. This process was tested in the home environment domain.