Open Cloze Question Generation using Masked Language Model

Abstract

Open cloze questions have been attracting attention for both measuring the ability and facilitating the learning of L2 English learners. In spite of its benefits, the open cloze test has been introduced only sporadically on the educational front, primarily because it is burdensome for teachers to create the questions manually. Unlike the more commonly used multiple choice questions (MCQ), open cloze questions are in free form and thus teachers have to ensure that only a ground truth answer and no additional words will be accepted in the blank. To help ease this burden, we developed CLOZER, an automatic open cloze question generator. The quantitative experiments show statistically that it can successfully generate open cloze questions that only accept the ground truth answer. Additionally, a field study at a local high school reveals the benefits and hurdles when introducing CLOZER.