Some Research Issues for KB Refinement
- The selection of the analogous examples generated by the agent (for
instance, examples that also represent a validation set for the rule);
- Powerful generalization and specialization methods for the rule's
bounds should be developed (e.g. methods for generalization and specialization
of numeric elements);
- Methods to facilitate the explanation of negative examples and automated
generation of appropriate negations of these explanations;
- Methods to guide the refinement of rules by using other sources
of information besides the expert (e.g. a repository of existing examples).




