Automated EA-type question generation from annotated texts

Abstract

The field of automated question generation is an active investigated area within the development of e-learning systems. The paper gives first an overview of the main methods and then the architecture of the proposed system is presented in details. The novelty of the proposed application lies in the target language Hungarian and in the application of soft computing methods for generation of semi-synonyms as no free thesaurus is available for the target language. The last part of the paper shows an example process of test generation.