ChicHealth @ MEDIQA 2021: Exploring the limits of pre-trained seq2seq models for medical summarization

Liwen Xu, Yan Zhang, Lei Hong, Yi Cai, Szui Sung


Abstract
In this article, we will describe our system for MEDIQA2021 shared tasks. First, we will describe the method of the second task, multiple answer summary (MAS). For extracting abstracts, we follow the rules of (CITATION). First, the candidate sentences are roughly estimated by using the Roberta model. Then the Markov chain model is used to evaluate the sentences in a fine-grained manner. Our team won the first place in overall performance, with the fourth place in MAS task, the seventh place in RRS task and the eleventh place in QS task. For the QS and RRS tasks, we investigate the performanceS of the end-to-end pre-trained seq2seq model. Experiments show that the methods of adversarial training and reverse translation are beneficial to improve the fine tuning performance.
Anthology ID:
2021.bionlp-1.29
Volume:
Proceedings of the 20th Workshop on Biomedical Language Processing
Month:
June
Year:
2021
Address:
Online
Venue:
BioNLP
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
263–267
Language:
URL:
https://aclanthology.org/2021.bionlp-1.29
DOI:
10.18653/v1/2021.bionlp-1.29
Bibkey:
Cite (ACL):
Liwen Xu, Yan Zhang, Lei Hong, Yi Cai, and Szui Sung. 2021. ChicHealth @ MEDIQA 2021: Exploring the limits of pre-trained seq2seq models for medical summarization. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 263–267, Online. Association for Computational Linguistics.
Cite (Informal):
ChicHealth @ MEDIQA 2021: Exploring the limits of pre-trained seq2seq models for medical summarization (Xu et al., BioNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.bionlp-1.29.pdf