It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books

TL;DR

This paper presents an automated question-answer pair generation system tailored for children's storybooks, aiming to enhance educational tools by testing various comprehension skills, supported by a new dataset and outperforming existing models.

Contribution

The paper introduces a novel QAG system for educational stories, utilizing a new dataset and demonstrating superior performance over existing baselines.

Findings

The QAG system outperforms state-of-the-art baselines.

A new annotated dataset with 278 storybooks and 10,580 QA pairs was created.

The system supports interactive storytelling applications.

Abstract

Existing question answering (QA) techniques are created mainly to answer questions asked by humans. But in educational applications, teachers often need to decide what questions they should ask, in order to help students to improve their narrative understanding capabilities. We design an automated question-answer generation (QAG) system for this education scenario: given a story book at the kindergarten to eighth-grade level as input, our system can automatically generate QA pairs that are capable of testing a variety of dimensions of a student's comprehension skills. Our proposed QAG model architecture is demonstrated using a new expert-annotated FairytaleQA dataset, which has 278 child-friendly storybooks with 10,580 QA pairs. Automatic and human evaluations show that our model outperforms state-of-the-art QAG baseline systems. On top of our QAG system, we also start to build an interactive story-telling application for the future real-world deployment in this educational scenario.