NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers

Lung Hao Lee; Po Han Chen; Yu Xiang Zeng; Po Lei Lee; Kuo Kai Shyu

NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers

Lung Hao Lee, Po Han Chen, Yu Xiang Zeng, Po Lei Lee, Kuo Kai Shyu

Department of Electrical Engineering

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

5 Scopus citations

Abstract

This study describes the model design of the NCUEE-NLP system for the MEDIQA challenge at the BioNLP 2021 workshop. We use the PEGASUS transformers and fine-tune the downstream summarization task using our collected and processed datasets. A total of 22 teams participated in the consumer health question summarization task of MEDIQA 2021. Each participating team was allowed to submit a maximum of ten runs. Our best submission, achieving a ROUGE2-F1 score of 0.1597, ranked third among all 128 submissions.

Original language	English
Title of host publication	Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021
Editors	Dina Demner-Fushman, Kevin Bretonnel Cohen, Sophia Ananiadou, Junichi Tsujii
Publisher	Association for Computational Linguistics (ACL)
Pages	268-272
Number of pages	5
ISBN (Electronic)	9781954085404
State	Published - 2021
Event	20th Workshop on Biomedical Language Processing, BioNLP 2021 - Virtual, Online Duration: 11 Jun 2021 → …

Publication series

Name	Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021

Conference

Conference	20th Workshop on Biomedical Language Processing, BioNLP 2021
City	Virtual, Online
Period	11/06/21 → …

Chinese Knowledge Base Construction and Applications for Medical Healthcare Domain(2/3)
Lee, L.-H. (PI)
1/05/20 → 30/04/21
Project: Research
Intelligent Interactive Platform with Applications to Healthcare and Home Care – Development of Artificial Intelligence – Based Brain Computer Interface( II )
Shyu, K.-K. (PI)
1/01/19 → 31/12/19
Project: Research

Cite this

Lee, L. H., Chen, P. H., Zeng, Y. X., Lee, P. L., & Shyu, K. K. (2021). NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers. In D. Demner-Fushman, K. B. Cohen, S. Ananiadou, & J. Tsujii (Eds.), Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021 (pp. 268-272). (Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021). Association for Computational Linguistics (ACL).

Lee, Lung Hao ; Chen, Po Han ; Zeng, Yu Xiang et al. / NCUEE-NLP at MEDIQA 2021 : Health Question Summarization Using PEGASUS Transformers. Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021. editor / Dina Demner-Fushman ; Kevin Bretonnel Cohen ; Sophia Ananiadou ; Junichi Tsujii. Association for Computational Linguistics (ACL), 2021. pp. 268-272 (Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021).

@inproceedings{54d9d23428aa4a20803c3f95985c7b0c,

title = "NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers",

abstract = "This study describes the model design of the NCUEE-NLP system for the MEDIQA challenge at the BioNLP 2021 workshop. We use the PEGASUS transformers and fine-tune the downstream summarization task using our collected and processed datasets. A total of 22 teams participated in the consumer health question summarization task of MEDIQA 2021. Each participating team was allowed to submit a maximum of ten runs. Our best submission, achieving a ROUGE2-F1 score of 0.1597, ranked third among all 128 submissions.",

author = "Lee, {Lung Hao} and Chen, {Po Han} and Zeng, {Yu Xiang} and Lee, {Po Lei} and Shyu, {Kuo Kai}",

note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics; 20th Workshop on Biomedical Language Processing, BioNLP 2021 ; Conference date: 11-06-2021",

year = "2021",

language = "???core.languages.en_GB???",

series = "Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021",

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

pages = "268--272",

editor = "Dina Demner-Fushman and Cohen, {Kevin Bretonnel} and Sophia Ananiadou and Junichi Tsujii",

booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021",

}

Lee, LH, Chen, PH, Zeng, YX, Lee, PL & Shyu, KK 2021, NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers. in D Demner-Fushman, KB Cohen, S Ananiadou & J Tsujii (eds), Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021. Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021, Association for Computational Linguistics (ACL), pp. 268-272, 20th Workshop on Biomedical Language Processing, BioNLP 2021, Virtual, Online, 11/06/21.

NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers. / Lee, Lung Hao; Chen, Po Han; Zeng, Yu Xiang et al.
Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021. ed. / Dina Demner-Fushman; Kevin Bretonnel Cohen; Sophia Ananiadou; Junichi Tsujii. Association for Computational Linguistics (ACL), 2021. p. 268-272 (Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021).

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

TY - GEN

T1 - NCUEE-NLP at MEDIQA 2021

T2 - 20th Workshop on Biomedical Language Processing, BioNLP 2021

AU - Lee, Lung Hao

AU - Chen, Po Han

AU - Zeng, Yu Xiang

AU - Lee, Po Lei

AU - Shyu, Kuo Kai

PY - 2021

Y1 - 2021

N2 - This study describes the model design of the NCUEE-NLP system for the MEDIQA challenge at the BioNLP 2021 workshop. We use the PEGASUS transformers and fine-tune the downstream summarization task using our collected and processed datasets. A total of 22 teams participated in the consumer health question summarization task of MEDIQA 2021. Each participating team was allowed to submit a maximum of ten runs. Our best submission, achieving a ROUGE2-F1 score of 0.1597, ranked third among all 128 submissions.

AB - This study describes the model design of the NCUEE-NLP system for the MEDIQA challenge at the BioNLP 2021 workshop. We use the PEGASUS transformers and fine-tune the downstream summarization task using our collected and processed datasets. A total of 22 teams participated in the consumer health question summarization task of MEDIQA 2021. Each participating team was allowed to submit a maximum of ten runs. Our best submission, achieving a ROUGE2-F1 score of 0.1597, ranked third among all 128 submissions.

UR - http://www.scopus.com/inward/record.url?scp=85123920632&partnerID=8YFLogxK

M3 - 會議論文篇章

AN - SCOPUS:85123920632

T3 - Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021

SP - 268

EP - 272

BT - Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021

A2 - Demner-Fushman, Dina

A2 - Cohen, Kevin Bretonnel

A2 - Ananiadou, Sophia

A2 - Tsujii, Junichi

PB - Association for Computational Linguistics (ACL)

Y2 - 11 June 2021

ER -

Lee LH, Chen PH, Zeng YX, Lee PL , Shyu KK. NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers. In Demner-Fushman D, Cohen KB, Ananiadou S, Tsujii J, editors, Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021. Association for Computational Linguistics (ACL). 2021. p. 268-272. (Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021).

NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers

Abstract

Publication series

Conference

Fingerprint

Projects

Chinese Knowledge Base Construction and Applications for Medical Healthcare Domain(2/3)

Intelligent Interactive Platform with Applications to Healthcare and Home Care – Development of Artificial Intelligence – Based Brain Computer Interface( II )

Cite this