paht_nlp @ MEDIQA 2021: Multi-grained Query Focused Multi-Answer Summarization

Wei Zhu, Yilong He, Ling Chai, Yunxiao Fan, Yuan Ni, Guotong Xie, Xiaoling Wang


Abstract
In this article, we describe our systems for the MEDIQA 2021 Shared Tasks. First, we will describe our method for the second task, Multi-Answer Summarization (MAS). For extractive summarization, two series of methods are applied. The first one follows (CITATION). First a RoBERTa model is first applied to give a local ranking of the candidate sentences. Then a Markov Chain model is applied to evaluate the sentences globally. The second method applies cross-sentence contextualization to improve the local ranking and discard the global ranking step. Our methods achieve the 1st Place in the MAS task. For the question summarization (QS) and radiology report summarization (RRS) tasks, we explore how end-to-end pre-trained seq2seq model perform. A series of tricks for improving the fine-tuning performances are validated.
Anthology ID:
2021.bionlp-1.10
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:
96–102
Language:
URL:
https://aclanthology.org/2021.bionlp-1.10
DOI:
10.18653/v1/2021.bionlp-1.10
Bibkey:
Cite (ACL):
Wei Zhu, Yilong He, Ling Chai, Yunxiao Fan, Yuan Ni, Guotong Xie, and Xiaoling Wang. 2021. paht_nlp @ MEDIQA 2021: Multi-grained Query Focused Multi-Answer Summarization. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 96–102, Online. Association for Computational Linguistics.
Cite (Informal):
paht_nlp @ MEDIQA 2021: Multi-grained Query Focused Multi-Answer Summarization (Zhu et al., BioNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.bionlp-1.10.pdf
Data
MS MARCO