An Ontology-Based System for Generating Mathematical Test Papers
- 607 Downloads
Automatic test paper generation is highly helpful in teaching and learning. In order to generate a test paper that covers as many knowledge points as possible, it is needed to discover knowledge points from exam questions. However, the problem of automatically finding knowledge points is seldom investigated in existing work. To fill this gap, this paper proposes an ontology-based method to discover knowledge points from mathematical exam questions. Accordingly, a system for automatically generating mathematical test papers is also proposed. It composes a test paper by solving a pseudo-Boolean optimization problem. Its practicality is demonstrated by a task of generating mathematical test papers from hundreds of postgraduate entrance exam questions.
KeywordsTest Paper Generation Exam Questions Knowledge Points Postgraduate Entrance Exam PBO Problem
This work is partly supported by the NSFC grants (61375056 and 61005043), the Guangdong Natural Science Foundation (S2013010012928), the Undergraduate Innovative Experiment Projects in Guangdong University of Foreign Studies (1184613038 and 201411846043), and the Business Intelligence Key Team of Guangdong University of Foreign Studies (TD1202).
- 1.Baader, F., Calvanese, D., McGuinness, D.L., Nardi, D., Patel-Schneider, P.F. (eds.): The Description Logic Handbook: Theory, Implementation, and Applications. Cambridge University Press, Cambridge (2003)Google Scholar
- 2.Du, J., Qi, G., Pan, J., Shen, Y.: Approximating linear order inference in OWL 2 DL by horn compilation. In: Proceedings of 2012 IEEE/WIC/ACM International Conferences on Web Intelligence, pp. 97–104 (2012)Google Scholar
- 5.Horrocks, I., Kutz, O., Sattler, U.: The even more irresistible \(\cal SROIQ\). In: Proceedings of the 10th International Conference on Principles of Knowledge Representation and Reasoning, pp. 57–67 (2006)Google Scholar