An Ontology-Based System for Generating Mathematical Test Papers

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.

[1]  Jianfeng Du,et al.  Approximating Linear Order Inference in OWL 2 DL by Horn Compilation , 2012, 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology.

[2]  Boris Motik,et al.  OWL 2: The next step for OWL , 2008, J. Web Semant..

[3]  Siu Cheung Hui,et al.  Divide-and-conquer memetic algorithm for online multi-objective test paper generation , 2012, Memetic Computing.

[4]  Ian Horrocks,et al.  The Even More Irresistible SROIQ , 2006, KR.

[5]  Grigorios Tsoumakas,et al.  Multi-Label Classification: An Overview , 2007, Int. J. Data Warehous. Min..

[6]  Jian-Jun Hu,et al.  The Genetic Algorithm in the Test Paper Generation , 2011, WISM.

[7]  Diego Calvanese,et al.  The Description Logic Handbook: Theory, Implementation, and Applications , 2003, Description Logic Handbook.

[8]  Niklas Sörensson,et al.  Translating Pseudo-Boolean Constraints into SAT , 2006, J. Satisf. Boolean Model. Comput..