事例ベース推論における動的類似性の仮説論理プログラミングによる実現

抄録

In legal reasoning, judging from precedent cases is very important since precedent cases complements incompleteness of legal rules. Therefore, CBR systems such as HYPO have been studied. A main characteristics of such CBR systems in legal reasoning is that similarity between cases are dynamically changed according to contexts. For example, if the system is on the plaintiff side, it will retrieve similar cases which are in favor of the plaintiff side. On the other hand, if the system is on the defendant side, it will retrieve entirely different cases which are in favor of the defendant side based on another similarity measure which is different from the measure used for the sake of the plaintiff. This kind of similarity is naturally implemented in abductive logic programming since we can regard the dynamic similarity as abducible predicates and change these predicates by context. In this paper, we define a relevance criteria for dynamic similarity and show a translation method to abductive logic programming. Moreover, by using abducibles, we show how to construct an explanation why the current case is similar to the cited case.