Data Augmentation for Radiology Report Simplification

Ziyu Yang, Santhosh Cherian, Slobodan Vucetic


Abstract
This work considers the development of a text simplification model to help patients better understand their radiology reports. This paper proposes a data augmentation approach to address the data scarcity issue caused by the high cost of manual simplification. It prompts a large foundational pre-trained language model to generate simplifications of unlabeled radiology sentences. In addition, it uses paraphrasing of labeled radiology sentences. Experimental results show that the proposed data augmentation approach enables the training of a significantly more accurate simplification model than the baselines.
Anthology ID:
2023.findings-eacl.144
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1922–1932
Language:
URL:
https://aclanthology.org/2023.findings-eacl.144
DOI:
10.18653/v1/2023.findings-eacl.144
Bibkey:
Cite (ACL):
Ziyu Yang, Santhosh Cherian, and Slobodan Vucetic. 2023. Data Augmentation for Radiology Report Simplification. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1922–1932, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Data Augmentation for Radiology Report Simplification (Yang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.144.pdf
Dataset:
 2023.findings-eacl.144.dataset.zip
Video:
 https://aclanthology.org/2023.findings-eacl.144.mp4