Generating Answer Candidates for Quizzes and Answer-Aware Question Generators

TL;DR

This paper introduces a model for generating multiple answer candidates from text passages to facilitate automatic quiz question creation, addressing a previously overlooked aspect of question generation.

Contribution

The paper presents a novel model for generating answer candidates, enhancing automatic question generation systems by filling a key gap in existing research.

Findings

Our model outperforms baseline methods in answer candidate generation.

Generated answer candidates are useful for manual and automatic question creation.

The approach improves the overall quality of automated quiz question generation.

Abstract

In education, open-ended quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus automatic question generation has been proposed as a possible alternative. So far, the vast majority of research has focused on generating the question text, relying on question answering datasets with readily picked answers, and the problem of how to come up with answer candidates in the first place has been largely ignored. Here, we aim to bridge this gap. In particular, we propose a model that can generate a specified number of answer candidates for a given passage of text, which can then be used by instructors to write questions manually or can be passed as an input to automatic answer-aware question generators. Our experiments show that our proposed answer candidate generation model outperforms several baselines.