How to Engage Your Readers? Generating Guiding Questions to Promote Active Reading

TL;DR

This paper introduces GuidingQ, a dataset of 10,000 in-text questions from academic texts, analyzes their linguistic features, explores generation methods, and demonstrates their effectiveness in enhancing reading comprehension.

Contribution

It provides the first comprehensive dataset and analysis of in-text guiding questions, along with methods for automatic question generation and evaluation of their impact on reading comprehension.

Findings

Generated questions are nearly as effective as human questions in improving comprehension.

Capturing inter-question relationships improves question generation quality.

Identifying question position remains a challenge in automatic generation.

Abstract

Using questions in written text is an effective strategy to enhance readability. However, what makes an active reading question good, what the linguistic role of these questions is, and what is their impact on human reading remains understudied. We introduce GuidingQ, a dataset of 10K in-text questions from textbooks and scientific articles. By analyzing the dataset, we present a comprehensive understanding of the use, distribution, and linguistic characteristics of these questions. Then, we explore various approaches to generate such questions using language models. Our results highlight the importance of capturing inter-question relationships and the challenge of question position identification in generating these questions. Finally, we conduct a human study to understand the implication of such questions on reading comprehension. We find that the generated questions are of high quality and are almost as effective as human-written questions in terms of improving readers' memorization and comprehension.