Comtuter-aided generation of multiple-choice tests

Summary form only given. The paper describes a novel automatic procedure for the generation of multiple-choice tests from electronic documents. In addition to employing various NLP techniques including term extraction and shallow parsing, the system makes use of language resources such as corpora and ontologies. The system operates in a fully automatic mode and also a semiautomatic environment where the user is offered the option to post-edit the generated test items. The results from the conducted evaluation suggest that the new procedure is very effective saving time and labour considerably and that the test items produced with the help of the program are not of inferior quality to those produced manually.