Belief Augmented Frame Sets for Knowledge Representation in Spoken Dialog Systems

We propose a frame structure that is augmented with belief functions to model knowledge in a spoken dialog system. In addition we propose methods to combine belief functions in the network, and operations on the network to support a dialog manager. We show how our Belief Augmented Frames framework can be used to manage a spoken dialog system, and give a simple example on how knowledge can be represented and integrated.

• Type: Conference
• Year: 2003
• Where: IICAI
• Authors: Colin Keng-Yan Tan, Kim-Teng Lua
• Keywords: Belief Augmented Frames, Belief Functions, IICAI 2003, IICAI 2007, Spoken Dialog System