The instructional effectiveness of automatically generated exercises for learning French grammatical gender: preliminary results

Abstract

Research into Automatic Exercise Generation (AEG) contributes new tools aimed at reducing the barrier to creating practice material, but few have been deployed in actual instruction with real learners. The present study extends previous work by employing AEG technology in instruction with L2 learners to evaluate its pedagogical effectiveness. Thirty-two second language learners of French were assigned to either a treatment condition, who practised with generated exercises, or a control condition that did no extra work. Both groups completed pre-, post-, and delayed post-tests. Participants in the treatment condition also completed questionnaires that elicited data on their in-practice emotions and the situations in which they arose. Our preliminary results suggest that AEG-based instruction can be pedagogically effective and support positive learning experiences, help to identify aspects of the instruction that could be improved, and suggest that a peer review mechanism could have an important role in future CALL platforms that use generated exercises.