JEFF - Just Another EFFicient Reading Comprehension Test Generation

Abstract

We introduce a method for generating vocabulary questions on reading comprehension of a given English article. In our approach, the method involves selecting target words in the given English article, finding synonyms as answer keys, and generating seemingly reasonable words in context as distractors. At run-time, some target words in the inputted article will be identified as questions, and automatically generating one answer key and three distractors. We present a AQG (automatic question generation) system, JEFF, that applies the method to generate questions automatically. Evaluation on a set of questions generated by JEFF shows that the method is close to the human-designed ones.

Tasks

Reproductions