Automatic distractor generation for multiple-choice English vocabulary questions

Abstract

The use of automated systems in second-language learning could substantially reduce the workload of human teachers and test creators. This study proposes a novel method for automatically generating distractors for multiple-choice English vocabulary questions. The proposed method introduces new sources for collecting distractor candidates and utilises semantic similarity and collocation information when ranking the collected candidates. We evaluated the proposed method by administering the questions to real English learners. We further asked an expert to judge the quality of the distractors generated by the proposed method, a baseline method and humans. The results show that the proposed method produces fewer problematic distractors than the baseline method. Furthermore, the generated distractors have a quality that is comparable with that of human-made distractors.