In order to function effectively, agents, whether human or software, must be able to communicate and interact through common understandings and compatible conceptualisations. In a multi-cultural world, ontological differences are a fundamental obstacle that must be overcome before inter-cultural communication can occur. The purpose of this paper is to discuss the issues faced by agents operating in large-scale multi-cultural environments and to argue for systems that are tolerant of heterogeneity, illustrating the discussion with a running example of researching and comparing university web sites as a realistic scenario representative of many current knowledge management tasks that would benefit from agent assistance. We then discuss the efforts of the Intelligent Agent Laboratory toward designing such tolerant systems, giving a detailed presentation of the results of several implementations.
Lecture notes in computer science: advances in artificial intelligence: proceedings of the 14th Australian Joint Conference on Artificial Intelligence (AI 2001), Adelaide, South Australia, Australia, 10-14 December 2001 / M. Brooks, D. Corbett and M. Stumptner (eds.),
Vol. 2256, pp. 321-332