Defining Explanation in Probabilistic Systems
This addresses the need for better explanation mechanisms in probabilistic systems, which is critical as they become more widely used, but it appears incremental by building on prior work.
The paper tackles the problem of defining and ordering explanations in probabilistic systems, showing that two existing approaches have significant issues and proposing a new combined approach.
As probabilistic systems gain popularity and are coming into wider use, the need for a mechanism that explains the system's findings and recommendations becomes more critical. The system will also need a mechanism for ordering competing explanations. We examine two representative approaches to explanation in the literature - one due to Gärdenfors and one due to Pearl - and show that both suffer from significant problems. We propose an approach to defining a notion of "better explanation" that combines some of the features of both together with more recent work by Pearl and others on causality.