UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

KnowLab at RadSum23: comparing pre-trained language models in radiology report summarization

Wu, J; Shi, D; Hasan, A; Wu, H; (2023) KnowLab at RadSum23: comparing pre-trained language models in radiology report summarization. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics. (pp. pp. 535-540). ACL: Toronto, Canada. Green open access

[thumbnail of 2023.bionlp-1.54.pdf]
Preview
Text
2023.bionlp-1.54.pdf - Published Version

Download (99kB) | Preview

Abstract

This paper presents our contribution to the RadSum23 shared task organized as part of the BioNLP 2023. We compared state-of-the-art generative language models in generating high-quality summaries from radiology reports. A two-stage fine-tuning approach was introduced for utilizing knowledge learnt from different datasets. We evaluated the performance of our method using a variety of metrics, including BLEU, ROUGE, Bertscore, CheXbert, and RadGraph. Our results revealed the potentials of different models in summarizing radiology reports and demonstrated the effectiveness of the two-stage fine-tuning approach. We also discussed the limitations and future directions of our work, highlighting the need for better understanding the architecture design’s effect and optimal way of fine-tuning accordingly in automatic clinical summarizations.

Type: Proceedings paper
Title: KnowLab at RadSum23: comparing pre-trained language models in radiology report summarization
Event: The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks
Dates: Jul 2023 - Jul 2023
ISBN-13: 9781959429852
Open access status: An open access version is available from UCL Discovery
DOI: 10.18653/v1/2023.bionlp-1.54
Publisher version: http://dx.doi.org/10.18653/v1/2023.bionlp-1.54
Language: English
Additional information: ACL materials are Copyright © 1963–2023 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > Institute of Health Informatics
URI: https://discovery.ucl.ac.uk/id/eprint/10181862
Downloads since deposit
34Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item