Diversity Enhanced Narrative Question Generation for Storybooks

TL;DR

This paper presents a multi-question generation model that produces diverse, answerable questions from storybook contexts, improving question variety and relevance for educational and conversational applications.

Contribution

The paper introduces a novel multi-question generation model (mQG) that enhances diversity and answerability in generated questions, validated on storybook datasets and adapted to other datasets.

Findings

mQG generates diverse, answerable questions effectively.

The model outperforms strong baselines on multiple metrics.

Zero-shot adaptation demonstrates versatility across datasets.

Abstract

Question generation (QG) from a given context can enhance comprehension, engagement, assessment, and overall efficacy in learning or conversational environments. Despite recent advancements in QG, the challenge of enhancing or measuring the diversity of generated questions often remains unaddressed. In this paper, we introduce a multi-question generation model (mQG), which is capable of generating multiple, diverse, and answerable questions by focusing on context and questions. To validate the answerability of the generated questions, we employ a SQuAD2.0 fine-tuned question answering model, classifying the questions as answerable or not. We train and evaluate mQG on the FairytaleQA dataset, a well-structured QA dataset based on storybooks, with narrative questions. We further apply a zero-shot adaptation on the TellMeWhy and SQuAD1.1 datasets. mQG shows promising results across various evaluation metrics, among strong baselines.