Few-shot fine-tuning SOTA summarization models for medical dialogues

David Fraile Navarro; Mark Dras; Shlomo Berkovsky

doi:10.18653/v1/2022.naacl-srw.32

Few-shot fine-tuning SOTA summarization models for medical dialogues

David Fraile Navarro, Mark Dras, Shlomo Berkovsky

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

14 Citations (Scopus)

92 Downloads (Pure)

Abstract

Abstractive summarization of medical dialogues presents a challenge for standard training approaches given the paucity of suitable datasets. We explore the performance of state-of-the-art models with zero-shot and few-shot learning strategies and measure the impact of pretraining with general domain and dialogue specific text on the summarization performance.

Original language	English
Title of host publication	The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Subtitle of host publication	Proceedings of the Student Research Workshop
Place of Publication	Stroudsburg, PA, USA
Publisher	Association for Computational Linguistics (ACL)
Pages	254-266
Number of pages	13
ISBN (Electronic)	9781955917735
DOIs	https://doi.org/10.18653/v1/2022.naacl-srw.32
Publication status	Published - Jul 2022
Event	2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Seattle, United States Duration: 10 Jul 2022 → 15 Jul 2022

Workshop

Workshop	2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Country/Territory	United States
City	Seattle
Period	10/07/22 → 15/07/22

Bibliographical note

Copyright the Publisher 2022. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Access to Document

10.18653/v1/2022.naacl-srw.32

Publisher version (open access)Final published version, 794 KBLicence: CC BY

https://aclanthology.org/2022.naacl-srw.32/Licence: CC BY

Cite this

Fraile Navarro, D., Dras, M., & Berkovsky, S. (2022). Few-shot fine-tuning SOTA summarization models for medical dialogues. In The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Student Research Workshop (pp. 254-266). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.naacl-srw.32

Fraile Navarro, David ; Dras, Mark ; Berkovsky, Shlomo. / Few-shot fine-tuning SOTA summarization models for medical dialogues. The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Student Research Workshop. Stroudsburg, PA, USA : Association for Computational Linguistics (ACL), 2022. pp. 254-266

@inproceedings{d552a4ab4a1e46169ce917b563b374db,

title = "Few-shot fine-tuning SOTA summarization models for medical dialogues",

abstract = "Abstractive summarization of medical dialogues presents a challenge for standard training approaches given the paucity of suitable datasets. We explore the performance of state-of-the-art models with zero-shot and few-shot learning strategies and measure the impact of pretraining with general domain and dialogue specific text on the summarization performance.",

author = "\{Fraile Navarro\}, David and Mark Dras and Shlomo Berkovsky",

note = "Copyright the Publisher 2022. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.; 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ; Conference date: 10-07-2022 Through 15-07-2022",

year = "2022",

month = jul,

doi = "10.18653/v1/2022.naacl-srw.32",

language = "English",

pages = "254--266",

booktitle = "The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",

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

address = "United States",

}

Fraile Navarro, D , Dras, M & Berkovsky, S 2022, Few-shot fine-tuning SOTA summarization models for medical dialogues. in The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Student Research Workshop. Association for Computational Linguistics (ACL), Stroudsburg, PA, USA, pp. 254-266, 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, Washington, United States, 10/07/22. https://doi.org/10.18653/v1/2022.naacl-srw.32

Few-shot fine-tuning SOTA summarization models for medical dialogues. / Fraile Navarro, David ; Dras, Mark ; Berkovsky, Shlomo.
The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Student Research Workshop. Stroudsburg, PA, USA: Association for Computational Linguistics (ACL), 2022. p. 254-266.

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

TY - GEN

T1 - Few-shot fine-tuning SOTA summarization models for medical dialogues

AU - Fraile Navarro, David

AU - Dras, Mark

AU - Berkovsky, Shlomo

N1 - Copyright the Publisher 2022. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2022/7

Y1 - 2022/7

N2 - Abstractive summarization of medical dialogues presents a challenge for standard training approaches given the paucity of suitable datasets. We explore the performance of state-of-the-art models with zero-shot and few-shot learning strategies and measure the impact of pretraining with general domain and dialogue specific text on the summarization performance.

AB - Abstractive summarization of medical dialogues presents a challenge for standard training approaches given the paucity of suitable datasets. We explore the performance of state-of-the-art models with zero-shot and few-shot learning strategies and measure the impact of pretraining with general domain and dialogue specific text on the summarization performance.

UR - https://www.scopus.com/pages/publications/85137584657

U2 - 10.18653/v1/2022.naacl-srw.32

DO - 10.18653/v1/2022.naacl-srw.32

M3 - Conference proceeding contribution

SP - 254

EP - 266

BT - The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg, PA, USA

T2 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Y2 - 10 July 2022 through 15 July 2022

ER -

Fraile Navarro D , Dras M , Berkovsky S. Few-shot fine-tuning SOTA summarization models for medical dialogues. In The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Proceedings of the Student Research Workshop. Stroudsburg, PA, USA: Association for Computational Linguistics (ACL). 2022. p. 254-266 doi: 10.18653/v1/2022.naacl-srw.32

Few-shot fine-tuning SOTA summarization models for medical dialogues

Abstract

Workshop

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this