Explanation Styles in iDocument
Björn Forcher; Benjamin Adrian; Thomas Roth-Berghofer
In: Thomas Roth-Berghofer; Stefan Schulz; Daniel Bahls; David B. Leake (Hrsg.). Proceedings of the Third International Workshop on Explanation-aware Computing. International Workshop on Explanation-aware Computing, 3rd, located at 18th European Conference on Artificial Intelligence ECAI 2008, July 21-22, Patras, Greece, Pages 144-156, Vol. 39, CEUR-WS.org, Aachen, 2008.
The information extraction system iDocument interactively extracts information from text such as instances and relations with respect to existing background knowledge. An extraction process creates weighted recommendations describing indications of relevant information. During execution, each process step records its output into an instantiated process model. We reused these bits of information for generating conceptual, functional as well as causal explanations. The purpose of these explanations is to illustrate the evolution of recommendations for convincing users of their validity. In order to visualise explanations, our component utilises different mechanisms for textual, tabular, and graphical rendering styles.