BDKG at MEDIQA 2021: System Report for the Radiology Report Summarization Task

Songtai Dai, Quan Wang, Yajuan Lyu, Yong Zhu


Abstract
This paper presents our winning system at the Radiology Report Summarization track of the MEDIQA 2021 shared task. Radiology report summarization automatically summarizes radiology findings into free-text impressions. This year’s task emphasizes the generalization and transfer ability of participating systems. Our system is built upon a pre-trained Transformer encoder-decoder architecture, i.e., PEGASUS, deployed with an additional domain adaptation module to particularly handle the transfer and generalization issue. Heuristics like ensemble and text normalization are also used. Our system is conceptually simple yet highly effective, achieving a ROUGE-2 score of 0.436 on test set and ranked the 1st place among all participating systems.
Anthology ID:
2021.bionlp-1.11
Volume:
Proceedings of the 20th Workshop on Biomedical Language Processing
Month:
June
Year:
2021
Address:
Online
Venues:
BioNLP | NAACL
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
103–111
Language:
URL:
https://aclanthology.org/2021.bionlp-1.11
DOI:
10.18653/v1/2021.bionlp-1.11
Bibkey:
Cite (ACL):
Songtai Dai, Quan Wang, Yajuan Lyu, and Yong Zhu. 2021. BDKG at MEDIQA 2021: System Report for the Radiology Report Summarization Task. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 103–111, Online. Association for Computational Linguistics.
Cite (Informal):
BDKG at MEDIQA 2021: System Report for the Radiology Report Summarization Task (Dai et al., BioNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.bionlp-1.11.pdf