Functional Modules of a Semi-automatic Question Generating System

In the last decade different applications of computer science (data mining, text mining) have been recognised. Presently an automatic question generation is a current research area. The elaborated system generates multi-choice questions from textbooks without using an external semantic database. Main demands made for the implemented automatic question generation system: supporting the Hungarian language, using a free grammar analytic, generating test questions from annotated texts, implementing potential answers from an internal, own developed semantic data base, supporting multi-choice problems, a possibility of implementing electronic and printable test papers. During planning the framework among the applied methods, clustering on the base of distances, a classification algorithm on the base of a neural net, in the case of generating questions and answer alternatives an own developed semantic data base was implemented. To prove the practical applicability of the automated question generating method, Java-language software was developed.