ABSTRACT
Developing intelligent tutoring systems (ITS) for a target domain includes authoring tasks requiring long time and efforts. Letting authors use natural language to represent various kinds of knowledge is a way that any authors can add and update knowledge easily. An authoring system acquiring knowledge represented in natural language for an equation-based tutor (Pyrenees) is presented in this paper. This authoring system was designed to acquire not only problem statements, but also commonsense and domain knowledge in natural language from authors.
- Gordon S. Novak Jr., "Representations of Knowledge in a Program for Solving Physics Problems", IJCAI-77, Cambridge, MA, 1977, pp. 286--291. Google ScholarDigital Library
- Opencyc.org, "OpenCyc Tutorial", http://www.cyc.com/cyc/opencyc/overview.Google Scholar
- Alan Bundy, et. al., "Solving mechanics problems using meta-level inference", IJCAI, 1979, pp. 1017--1027. Google ScholarDigital Library
- Steven Ritter, et. al., "Authoring Content in the PAT Algebra Tutor", Journal of Interactive Media in Education, 1998 (9), pp. 1--30.Google Scholar
- Kurt VanLehn., et. al., "Implicit versus explicit learning of strategies in a non-procedural cognitive skill", Intelligent Tutoring Systems: 7th Intern'l Conf. (pp. 521--530). 2004, Berlin.Google Scholar
- Timothy Chklovski, "Learner: a system for acquiring commonsense knowledge by analogy", K-CAP'03:4--12 Google ScholarDigital Library
- Robert Speer, "Open Mind Commons: An Inquisitive Approach to Learning Common Sense", Workshop on Common Sense and Intelligent User Interfaces, 2007.Google Scholar
- Bill MacCartney and Christopher D. Manning, "Modeling semantic containment and exclusion in natural language inference", Coling-08, Manchester, UK, 2008 Google ScholarDigital Library
- Norbert E. Fuchs, Kaarel Kaljurand, and Tobias Kuhn. "Attempto Controlled English for Knowledge Representation". In Reasoning Web, 4th Intern'l Summer School 2008, number 5224, pp. 104--124., 2008. Google ScholarDigital Library
Index Terms
- Using natural language to represent knowledge in an intelligent tutoring system
Recommendations
Developing an intelligent tutoring system using natural language for knowledge representation
ITS'10: Proceedings of the 10th international conference on Intelligent Tutoring Systems - Volume Part IIAuthoring the domain knowledge of an intelligent tutoring system (ITS) is a well-known problem, and an often-mentioned approach is to use authors who are domain experts Unfortunately, this approach requires that potential authors learn to write and ...
Knowledge Representation for Natural Language Understanding: The L_LILOG Approach
The logic-based knowledge representation language L_LILOG, which is used to represent both the semantic background knowledge as well as the information extracted from German texts within the LILOG project, is discussed. L_LILOG integrates frame-like ...
Comments