The ACACIA project is a multidisciplinary project that aims at offering models, methods and tools in order to help the knowledge engineer to acquire (i.e. elicit and model) knowledge from multiple expertise sources (experts or documents). The purpose is to capitalize expertise on a given field or to build a knowledge-based system.
We developed CGKAT, a tool allowing to build conceptual graphs from structured documents ; it manages hypertext links between elements of documents and a base of conceptual graphs ; it allows the user to search information in both the documents and the base, in answer to requests expressed in conceptual graphs.
We exploited CENTAUR to develop COKACE, a tool dedicated to CML (Conceptual Modelling Language), the language offered by COMMONKADS to describe expertise models.
For knowledge acquisition from multiple experts, we deepened our model of cognitive agent for guiding knowledge acquisition and our techniques of comparison of multiple expertise models : comparison of conceptual graphs, generation of consensus rules. We also studied extensions of COMMONKADS for multi-expertise and for building multi-agents systems.
We analysed explanatory dialogues among experts solving cooperatively a problem and we determined the explanatory strategies appearing in such dialogues. We deepened our modelling of explanation evaluation activity.
This year, the project was funded by :