Knowledge-Driven Distractor Generation for Cloze-style Multiple Choice Questions

Cloze-style multiple choice question (MCQ) is a common Automatically generating distractors has been previously form of exercise used to evaluate the proficiency of language explored as part of cloze-style MCQ construction in a few learners, frequently showing up in homework and online studies. However, those methods generally assume prior testings. Figure 1 shows a cloze-style MCQ, which typically knowledge of a specific domain (e.g., science) of the given consists of: a question stem with a blank to be filled question and then use corresponding domain-specific vocabulary in, the correct answer and multiple wrong answers used to as candidate distractor set, ranked by various unsupervised distract testees. Despite the high demand, manual crafting of similarity heuristics (Sumita, Sugaya, and Yamamoto such MCQs is highly time-consuming for educators, which 2005; Kumar, Banchs, and D'Haro 2015; Jiang and Lee calls for the automatic generation of as much practice material 2017; Ha and Yaneva 2018) or supervised machine as possible from readily available plain texts so that learning model (Sakaguchi, Arase, and Komachi 2013; formally usable quizzes can be generated after lightweight Welbl, Liu, and Gardner 2017; Liang et al. 2018).