Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks

Raseen Tariq; Sheza Malik; Mousumi Roy; Meena Z. Islam; Umair Rasheed; Jiang Bian; Kai Zheng; Rui Zhang

doi:10.1109/ICHI57859.2023.00136

Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks

Raseen Tariq, Sheza Malik, Mousumi Roy, Meena Z. Islam, Umair Rasheed, Jiang Bian, Kai Zheng, Rui Zhang

Surgery

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this study, we evaluated the performance of ChatGPT for various textual tasks regarding the information on dietary supplements. We found that ChatGPT performed reasonably well with text summarization, simplification and extracting relations. However, in about one third of sentences, human evaluators felts that some relevant information was lost among the output generated by ChatGPT.

Original language	English (US)
Title of host publication	Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	746-749
Number of pages	4
ISBN (Electronic)	9798350302639
DOIs	https://doi.org/10.1109/ICHI57859.2023.00136
State	Published - 2023
Event	11th IEEE International Conference on Healthcare Informatics, ICHI 2023 - Houston, United States Duration: Jun 26 2023 → Jun 29 2023

Publication series

Name	Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023

Conference

Conference	11th IEEE International Conference on Healthcare Informatics, ICHI 2023
Country/Territory	United States
City	Houston
Period	6/26/23 → 6/29/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

ChatGPT
relation extraction
text simplification
text summarization

Access

10.1109/ICHI57859.2023.00136

OpenUrl availability

Full text

Cite this

Tariq, R., Malik, S., Roy, M., Islam, M. Z., Rasheed, U., Bian, J., Zheng, K., & Zhang, R. (2023). Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks. In Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023 (pp. 746-749). (Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI57859.2023.00136

Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks. / Tariq, Raseen; Malik, Sheza; Roy, Mousumi et al.
Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 746-749 (Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Tariq, R, Malik, S, Roy, M, Islam, MZ, Rasheed, U, Bian, J, Zheng, K & Zhang, R 2023, Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks. in Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023. Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023, Institute of Electrical and Electronics Engineers Inc., pp. 746-749, 11th IEEE International Conference on Healthcare Informatics, ICHI 2023, Houston, United States, 6/26/23. https://doi.org/10.1109/ICHI57859.2023.00136

Tariq R, Malik S, Roy M, Islam MZ, Rasheed U, Bian J et al. Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks. In Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 746-749. (Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023). doi: 10.1109/ICHI57859.2023.00136

Tariq, Raseen ; Malik, Sheza ; Roy, Mousumi et al. / Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks. Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 746-749 (Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023).

@inproceedings{bd741f1f72a94778b0134337f798c7f9,

title = "Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks",

abstract = "In this study, we evaluated the performance of ChatGPT for various textual tasks regarding the information on dietary supplements. We found that ChatGPT performed reasonably well with text summarization, simplification and extracting relations. However, in about one third of sentences, human evaluators felts that some relevant information was lost among the output generated by ChatGPT.",

keywords = "ChatGPT, relation extraction, text simplification, text summarization",

author = "Raseen Tariq and Sheza Malik and Mousumi Roy and Islam, {Meena Z.} and Umair Rasheed and Jiang Bian and Kai Zheng and Rui Zhang",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 11th IEEE International Conference on Healthcare Informatics, ICHI 2023 ; Conference date: 26-06-2023 Through 29-06-2023",

year = "2023",

doi = "10.1109/ICHI57859.2023.00136",

language = "English (US)",

series = "Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "746--749",

booktitle = "Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023",

}

TY - GEN

T1 - Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks

AU - Tariq, Raseen

AU - Malik, Sheza

AU - Roy, Mousumi

AU - Islam, Meena Z.

AU - Rasheed, Umair

AU - Bian, Jiang

AU - Zheng, Kai

AU - Zhang, Rui

PY - 2023

Y1 - 2023

N2 - In this study, we evaluated the performance of ChatGPT for various textual tasks regarding the information on dietary supplements. We found that ChatGPT performed reasonably well with text summarization, simplification and extracting relations. However, in about one third of sentences, human evaluators felts that some relevant information was lost among the output generated by ChatGPT.

AB - In this study, we evaluated the performance of ChatGPT for various textual tasks regarding the information on dietary supplements. We found that ChatGPT performed reasonably well with text summarization, simplification and extracting relations. However, in about one third of sentences, human evaluators felts that some relevant information was lost among the output generated by ChatGPT.

KW - ChatGPT

KW - relation extraction

KW - text simplification

KW - text summarization

UR - http://www.scopus.com/inward/record.url?scp=85181559132&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85181559132&partnerID=8YFLogxK

U2 - 10.1109/ICHI57859.2023.00136

DO - 10.1109/ICHI57859.2023.00136

M3 - Conference contribution

AN - SCOPUS:85181559132

T3 - Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023

SP - 746

EP - 749

BT - Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th IEEE International Conference on Healthcare Informatics, ICHI 2023

Y2 - 26 June 2023 through 29 June 2023

ER -

Assessing ChatGPT for Text Summarization, Simplification and Extraction Tasks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this