A Framework for Computer-Aided Design of Educational Domain Models
A Framework for Computer-Aided Design of Educational Domain Models
复制标题
DOI：
10.1007/978-3-319-73721-8_7
复制
发表时间：
2018-01
期刊：
影响因子：
--
通讯作者：
Eric Butler;Emina Torlak;Zoran Popovic
中科院分区：
文献类型：
--
作者：
Eric Butler;Emina Torlak;Zoran Popovic
许多教育应用，从辅导到问题生成，都是建立在给定领域的操作知识的正式模型上的。这些领域模型由专家用于解决领域问题的重写规则组成;例如，因式分解是K-12代数的一个这样的规则。领域模型目前需要数百个小时才能创建，并且它们在满足教育目标（例如最大化解决问题的效率）方面存在很大差异。快速、目标驱动的领域模型的创建是个性化教育工具开发中的一个关键挑战。本文提出了一个新的计算机辅助领域模型创作框架，用于教育应用。以一组示例问题（例如，）作为输入，解决这些问题的一组基本公理规则（例如，因子分解），以及表达期望的教育目标的函数。给定这些输入，它首先合成一组声音策略规则（例如，将多个公理整合到高级问题解决策略中。公理和策略，然后搜索一个域模型，优化的objective.is基于新的算法从例子和公理挖掘策略规范，从这些规范合成策略规则，并选择一个最佳的域模型从公理和tactics.We evaluateon域的K-12代数，发现它恢复教科书的战术和域模型，发现新的战术和模型，并优于一个先前的工具为这个领域的数量级。但推广超越K-12代数：我们还使用它来（重新）发现命题逻辑的证明策略，展示其帮助设计各种教育领域模型的潜力。
Many educational applications, from tutoring to problem generation, are built on a formal model of the operational knowledge for a given domain. Thesedomain modelsconsist of rewrite rules that experts apply to solve problems in the domain; e.g., factoring,, is one such rule for K-12 algebra. Domain models currently take hundreds of hours to create, and they differ widely in how well they meet educational objectives such as maximizing problem-solving efficiency. Rapid, objective-driven creation of domain models is a key challenge in the development of personalized educational tools.This paper presents, a new framework for computer-aided authoring of domain models for educational applications.takes as input a set of example problems (e.g.,), a set of basicaxiomrules for solving these problems (e.g., factoring), and a function expressing the desired educational objective. Given these inputs, it first synthesizes a set of soundtacticrules (e.g., combining like terms) that integrate multiple axioms into advanced problem-solving strategies. The axioms and tactics are then searched for a domain model that optimizes the objective.is based on new algorithms for mining tactic specifications from examples and axioms, synthesizing tactic rules from these specifications, and selecting an optimal domain model from the axioms and tactics.We evaluateon the domain of K-12 algebra, finding that it recovers textbook tactics and domain models, discovers new tactics and models, and outperforms a prior tool for this domain by orders of magnitude. Butgeneralizes beyond K-12 algebra: we also use it to (re)discover proof tactics for propositional logic, demonstrating its potential to aid in designing models for a variety of educational domains.