Assessing Relevance with Extensionally Defined Principles and Cases

Knowledge Representation and Reasoning

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 17

Case-Based Reasoning

Expert decision-makers often explain decisions by citing general principles. In some domains, however, it is nearly impossible to define principles intensionally so that they may be applied deductively. After investigating hundreds of professional ethics case opinions, we hypothesized that the decision-makers’ explanations extensionally defined principles over time, in effect, operationalizing them. To model this phenomenon computationally, we constructed SIROCCO, a system for retrieving principles and past cases. This paper presents empirical evidence that operationalization information can be leveraged to predict more accurately the principles and past cases that are relevant in the analysis of new cases.