How to Engage your Readers?: Generating Guiding Questions to Promote Active Reading

Peng Cui; Vilém Zouhar; Xiaoyu Zhang; Mrinmaya Sachan

doi:10.18653/v1/2024.acl-long.632

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

Peng Cui, Vilém Zouhar, Xiaoyu Zhang, Mrinmaya Sachan

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

2 Downloads (CityUHK Scholars)

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. ©2024 Association for Computational Linguistics

Original language	English
Title of host publication	Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics
Editors	Lun-Wei Ku, Andre Martins, Vivek Srikumar
Place of Publication	United States
Publisher	Association for Computational Linguistics
Pages	11749–11765
Number of pages	17
Volume	1
ISBN (Electronic)	979-8-89176-094-3
ISBN (Print)	979-8-89176-094-3
DOIs	https://doi.org/10.18653/v1/2024.acl-long.632
Publication status	Published - Aug 2024
Externally published	Yes
Event	62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) - Centara Grand and Bangkok Convention Centre, Bangkok, Thailand Duration: 11 Aug 2024 → 16 Aug 2024 https://aclanthology.org/2024.acl-long https://2024.aclweb.org/ https://aclanthology.org/ https://aclanthology.org/2024.acl-tutorials https://aclanthology.org/2024.findings-acl

Conference

Conference	62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)
Abbreviated title	ACL2024
Place	Thailand
City	Bangkok
Period	11/08/24 → 16/08/24
Internet address	https://aclanthology.org/2024.acl-long https://2024.aclweb.org/ https://aclanthology.org/ https://aclanthology.org/2024.acl-tutorials https://aclanthology.org/2024.findings-acl

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access Output

10.18653/v1/2024.acl-long.632

295041834.pdfFinal Published version, 1.06 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Cui, P., Zouhar, V., Zhang, X., & Sachan, M. (2024). How to Engage your Readers? Generating Guiding Questions to Promote Active Reading. In L.-W. Ku, A. Martins, & V. Srikumar (Eds.), Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Vol. 1, pp. 11749–11765). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.acl-long.632

@inproceedings{1fd675ef6d5644e5b6be282339c6e96e,

title = "How to Engage your Readers?: Generating Guiding Questions to Promote Active Reading",

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{\textquoteright} memorization and comprehension. {\textcopyright}2024 Association for Computational Linguistics",

author = "Peng Cui and Vil{\'e}m Zouhar and Xiaoyu Zhang and Mrinmaya Sachan",

year = "2024",

month = aug,

doi = "10.18653/v1/2024.acl-long.632",

language = "English",

isbn = "979-8-89176-094-3",

volume = "1",

pages = "11749–11765",

editor = "Lun-Wei Ku and Andre Martins and Vivek Srikumar",

booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

address = "United States",

note = "62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), ACL2024 ; Conference date: 11-08-2024 Through 16-08-2024",

url = "https://aclanthology.org/2024.acl-long, https://2024.aclweb.org/, https://aclanthology.org/, https://aclanthology.org/2024.acl-tutorials, https://aclanthology.org/2024.findings-acl",

}

Cui, P, Zouhar, V, Zhang, X & Sachan, M 2024, How to Engage your Readers? Generating Guiding Questions to Promote Active Reading. in L-W Ku, A Martins & V Srikumar (eds), Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. vol. 1, Association for Computational Linguistics, United States, pp. 11749–11765, 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), Bangkok, Thailand, 11/08/24. https://doi.org/10.18653/v1/2024.acl-long.632

How to Engage your Readers? Generating Guiding Questions to Promote Active Reading. / Cui, Peng; Zouhar, Vilém; Zhang, Xiaoyu et al.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. ed. / Lun-Wei Ku; Andre Martins; Vivek Srikumar. Vol. 1 United States: Association for Computational Linguistics, 2024. p. 11749–11765.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - How to Engage your Readers?

T2 - 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)

AU - Cui, Peng

AU - Zouhar, Vilém

AU - Zhang, Xiaoyu

AU - Sachan, Mrinmaya

PY - 2024/8

Y1 - 2024/8

N2 - 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. ©2024 Association for Computational Linguistics

AB - 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. ©2024 Association for Computational Linguistics

UR - http://www.scopus.com/inward/record.url?scp=85204473172&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85204473172&origin=recordpage

U2 - 10.18653/v1/2024.acl-long.632

DO - 10.18653/v1/2024.acl-long.632

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 979-8-89176-094-3

VL - 1

SP - 11749

EP - 11765

BT - Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics

A2 - Ku, Lun-Wei

A2 - Martins, Andre

A2 - Srikumar, Vivek

PB - Association for Computational Linguistics

CY - United States

Y2 - 11 August 2024 through 16 August 2024

ER -

Cui P, Zouhar V, Zhang X, Sachan M. How to Engage your Readers? Generating Guiding Questions to Promote Active Reading. In Ku LW, Martins A, Srikumar V, editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Vol. 1. United States: Association for Computational Linguistics. 2024. p. 11749–11765 doi: 10.18653/v1/2024.acl-long.632