A System that Generates Word Problems Using Problem Generation Episodes
Kazuaki Kojima, Kazuhisa Miwa · Institutional Repositories DataBase (IRDB) · 2005
In mathematical learning, it is important to give learners problems that have various features in both surface problem situations and deep mathematical structures. In this study, we implement a system that can generate various problems by altering those surface and structural features for mathematical word problems using problem generation episodes. Each problem generation episode is knowledge comprised of a base example problem and a new analogical instance, which is regarded as a past case where an analogical instance was generated from an example problem. Our system generates problems applying problem generation episodes to initial problems stored in the system. In this paper, we describe our approach for generating mathematical word problems, and perform preliminary experiments to verify whether our system can appropriately expand the variety of problems.