Explanation Interfaces for the Semantic Web: Issues and Models

Abstract

As the Semantic Web has enabled new application capabilities, new interaction modes arise and grow in importance. Applications can now not only retrieve results but also use term meanings to derive new results. Thus, explaining results has become an important new interaction mode for Semantic Web applications. The explanation interaction mode needs to provide transparency and accountability to application results. We have developed an explanation infrastructure that can provide Semantic Web consumers (humans and agents) with explanations for results, such as where results came from and how they were derived. We have addressed explanation requirements for applications that range from intelligent analyst assistants that leverage text analytics to transparent and accountable reasoning systems that protect user privacy. In this paper, we will describe some Semantic Web user interaction requirements and paradigms that are important for Semantic Web applications.