Alfred Hofmann et al.

School of Mathematical and Computing Sciences
Victoria University of Wellington
Wellington, New Zealand
xgao@mcs.vuw.ac.nz
- Department of Computer Science and Software Engineering
The University of Melbourne
Victoria, 3010, Australia
leon@cs.mu.oz.au

Knowledge-based Information Agents

Xiaoying Gao1 - Leon Sterling2

Abstract:

This paper explains our approach to building knowledge-based information agents. Instead of building an agent from scratch, we advocate building an agent by adding knowledge to a framework. Knowledge is classified into three categories - general knowledge, domain specific knowledge and site specific knowledge - which enables knowledge reuse and sharing. The paper details the agent architecture, the components of each category of knowledge and the main functions of the framework.

• Introduction
• Knowledge Classification
• Agent Architecture
• Three Knowledge Bases
• Information Extraction Engine
• Experimental Results
• Conclusion
• References
• About this document ...