Few-shot Question Generation for Reading Comprehension

Yin Poon; John S.Y. Lee; Yu Yan Lam; Wing Lam Suen; Elsie Li Chen Ong; Samuel Kai Wah Chu

Few-shot Question Generation for Reading Comprehension

Yin Poon
, John S.Y. Lee
, Yu Yan Lam
, Wing Lam Suen
, Elsie Li Chen Ong
, Samuel Kai Wah Chu

Academy of Wellness and Human Development

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

3 Citations (Scopus)

Abstract

According to the internationally recognized PIRLS (Progress in International Reading Literacy Study) assessment standards, reading comprehension questions should require not only information retrieval, but also higher-order processes such as inferencing, interpreting and evaluation. However, these kinds of questions are often not available in large quantities for training question generation models. This paper investigates whether pre-trained Large Language Models (LLMs) can produce higher-order questions. Human assessment on a Chinese dataset shows that few-shot LLM prompting generates more usable and higher-order questions than two competitive neural baselines.

Original language	English
Title of host publication	SIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop
Editors	Kam-Fai Wong, Min Zhang, Ruifeng Xu, Jing Li, Zhongyu Wei, Lin Gui, Bin Liang, Runcong Zhao
Publisher	Association for Computational Linguistics (ACL)
Pages	21-27
Number of pages	7
ISBN (Electronic)	9798891761551
Publication status	Published - Aug 2024
Event	10th SIGHAN Workshop on Chinese Language - Centara Grand and Bangkok Convention Centre, Bangkok, Thailand Duration: 16 Aug 2024 → 16 Aug 2024 https://aclanthology.org/volumes/2024.sighan-1/ (Proceedings of SIGHAN Workshop) https://sites.google.com/view/sighan2024/home (Workshop website)

Publication series

Name	SIGHAN - SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop

Conference

Conference	10th SIGHAN Workshop on Chinese Language
Abbreviated title	SIGHAN 2024
Country/Territory	Thailand
City	Bangkok
Period	16/08/24 → 16/08/24
Internet address	https://aclanthology.org/volumes/2024.sighan-1/ (Proceedings of SIGHAN Workshop) https://sites.google.com/view/sighan2024/home (Workshop website)

UN SDGs

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

SDG 4 Quality Education

Cite this

Poon, Y., Lee, J. S. Y., Lam, Y. Y., Suen, W. L., Ong, E. L. C., & Chu, S. K. W. (2024). Few-shot Question Generation for Reading Comprehension. In K.-F. Wong, M. Zhang, R. Xu, J. Li, Z. Wei, L. Gui, B. Liang, & R. Zhao (Eds.), SIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop (pp. 21-27). (SIGHAN - SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop). Association for Computational Linguistics (ACL).

Poon, Yin ; Lee, John S.Y. ; Lam, Yu Yan et al. / Few-shot Question Generation for Reading Comprehension. SIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop. editor / Kam-Fai Wong ; Min Zhang ; Ruifeng Xu ; Jing Li ; Zhongyu Wei ; Lin Gui ; Bin Liang ; Runcong Zhao. Association for Computational Linguistics (ACL), 2024. pp. 21-27 (SIGHAN - SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop).

@inproceedings{78e48b69369242188bce6518ce9483d2,

title = "Few-shot Question Generation for Reading Comprehension",

abstract = "According to the internationally recognized PIRLS (Progress in International Reading Literacy Study) assessment standards, reading comprehension questions should require not only information retrieval, but also higher-order processes such as inferencing, interpreting and evaluation. However, these kinds of questions are often not available in large quantities for training question generation models. This paper investigates whether pre-trained Large Language Models (LLMs) can produce higher-order questions. Human assessment on a Chinese dataset shows that few-shot LLM prompting generates more usable and higher-order questions than two competitive neural baselines.",

author = "Yin Poon and Lee, \{John S.Y.\} and Lam, \{Yu Yan\} and Suen, \{Wing Lam\} and Ong, \{Elsie Li Chen\} and Chu, \{Samuel Kai Wah\}",

note = "We gratefully acknowledge support from the e-Learning Ancillary Facilities Programme of the Quality Education Fund (Project “Knowledge Overlord - A Self-sustaining AI Game-based Online Platform to Enhance Student{\textquoteright}s Literacy Ability and 21st Century Skills”); and from a Teaching Development Grant at City University of Hong Kong (project 6000834). Publisher Copyright: {\textcopyright} 2024 Association for Computational Linguistics; 10th SIGHAN Workshop on Chinese Language, SIGHAN 2024 ; Conference date: 16-08-2024 Through 16-08-2024",

year = "2024",

month = aug,

language = "English",

series = "SIGHAN - SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop",

publisher = "Association for Computational Linguistics (ACL)",

pages = "21--27",

editor = "Kam-Fai Wong and Min Zhang and Ruifeng Xu and Jing Li and Zhongyu Wei and Lin Gui and Bin Liang and Runcong Zhao",

booktitle = "SIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop",

address = "Australia",

url = "https://aclanthology.org/volumes/2024.sighan-1/, https://sites.google.com/view/sighan2024/home",

}

Poon, Y, Lee, JSY, Lam, YY, Suen, WL, Ong, ELC & Chu, SKW 2024, Few-shot Question Generation for Reading Comprehension. in K-F Wong, M Zhang, R Xu, J Li, Z Wei, L Gui, B Liang & R Zhao (eds), SIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop. SIGHAN - SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop, Association for Computational Linguistics (ACL), pp. 21-27, 10th SIGHAN Workshop on Chinese Language, Bangkok, Thailand, 16/08/24.

Few-shot Question Generation for Reading Comprehension. / Poon, Yin; Lee, John S.Y.; Lam, Yu Yan et al.
SIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop. ed. / Kam-Fai Wong; Min Zhang; Ruifeng Xu; Jing Li; Zhongyu Wei; Lin Gui; Bin Liang; Runcong Zhao. Association for Computational Linguistics (ACL), 2024. p. 21-27 (SIGHAN - SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Few-shot Question Generation for Reading Comprehension

AU - Poon, Yin

AU - Lee, John S.Y.

AU - Lam, Yu Yan

AU - Suen, Wing Lam

AU - Ong, Elsie Li Chen

AU - Chu, Samuel Kai Wah

N1 - We gratefully acknowledge support from the e-Learning Ancillary Facilities Programme of the Quality Education Fund (Project “Knowledge Overlord - A Self-sustaining AI Game-based Online Platform to Enhance Student’s Literacy Ability and 21st Century Skills”); and from a Teaching Development Grant at City University of Hong Kong (project 6000834). Publisher Copyright: © 2024 Association for Computational Linguistics

PY - 2024/8

Y1 - 2024/8

N2 - According to the internationally recognized PIRLS (Progress in International Reading Literacy Study) assessment standards, reading comprehension questions should require not only information retrieval, but also higher-order processes such as inferencing, interpreting and evaluation. However, these kinds of questions are often not available in large quantities for training question generation models. This paper investigates whether pre-trained Large Language Models (LLMs) can produce higher-order questions. Human assessment on a Chinese dataset shows that few-shot LLM prompting generates more usable and higher-order questions than two competitive neural baselines.

AB - According to the internationally recognized PIRLS (Progress in International Reading Literacy Study) assessment standards, reading comprehension questions should require not only information retrieval, but also higher-order processes such as inferencing, interpreting and evaluation. However, these kinds of questions are often not available in large quantities for training question generation models. This paper investigates whether pre-trained Large Language Models (LLMs) can produce higher-order questions. Human assessment on a Chinese dataset shows that few-shot LLM prompting generates more usable and higher-order questions than two competitive neural baselines.

UR - https://aclanthology.org/2024.sighan-1.3/

UR - https://www.scopus.com/pages/publications/85204880373

M3 - Conference proceeding

AN - SCOPUS:85204880373

T3 - SIGHAN - SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop

SP - 21

EP - 27

BT - SIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop

A2 - Wong, Kam-Fai

A2 - Zhang, Min

A2 - Xu, Ruifeng

A2 - Li, Jing

A2 - Wei, Zhongyu

A2 - Gui, Lin

A2 - Liang, Bin

A2 - Zhao, Runcong

PB - Association for Computational Linguistics (ACL)

T2 - 10th SIGHAN Workshop on Chinese Language

Y2 - 16 August 2024 through 16 August 2024

ER -

Poon Y, Lee JSY, Lam YY, Suen WL, Ong ELC, Chu SKW. Few-shot Question Generation for Reading Comprehension. In Wong KF, Zhang M, Xu R, Li J, Wei Z, Gui L, Liang B, Zhao R, editors, SIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2024. p. 21-27. (SIGHAN - SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop).

Few-shot Question Generation for Reading Comprehension

Abstract

Publication series

Conference

UN SDGs

Other files and links

Fingerprint

Cite this