Knowledge enhanced embodied cognitive interaction technologies

In the project we aim to connect two yet unrelated areas of modeling cognitive systems with semantic webtechnologies as a central research line of text technology. More specifically, this relates to distributed cognition (Hollan et al., 2000) as exemplified by rising web technologies e.g. collaborative tagging and social ontologies (Steels, 2006) on the one hand and artificial cognition based on embodied virtual humanoid agents e.g. MAX (Kopp and Wachsmuth, 2004) on the other hand. The aim of the project is to enhance the latter by exploring the former as the agentsâ primary knowledge resource and, thus, to make virtual humans more situation and topic aware. In doing so we need to overcome a central deficit of social ontologies, that is, their low level of standardization and high degree of dynamics, respectively. This is exemplified by Wikipedias category system which is organized far away from being operational for the task of artificial cognitive interaction. Thus, a central task of bridging artificial embodied agents with social ontologies is the text technological reconstruction of social ontologies in terms of an appropriate semantic database. The project's research is in the line of efforts to utilize social tagging systems as, e.g., the Wikipedia, wikimanuals and other special wikis, which provide large resources of encyclopedic knowledge (Mehler 2008). In this context, we plan to exploit object knowledge as well as linguistic and metalinguistic knowledge (by example of so called wiktionaries) in a way that enables virtual agents to identify, label, track and to continue the topic of a dialogue to which they participate as the interlocutor of a human user. As a result we plan to enable virtual agents to answer questions as well as to detect topic changes and to react meaningful facing this kind of dialogical dynamics. Consequently, to build more adequate models of thematic dialogue management in conjunction with their implementation and exhaustive empirical testing will be a major goal of the planned project. In summary, we aim at an enabling technology of all those cognitive interaction technologies which integrate semantic means of interaction with human users. This is of relevance to all those projects of the EC which deal with situational communication.

[view:groupmembers==207]