TY - GEN
T1 - paht_nlp @ MEDIQA 2021
T2 - 20th Workshop on Biomedical Language Processing, BioNLP 2021
AU - Zhu, Wei
AU - He, Yilong
AU - Chai, Ling
AU - Fan, Yunxiao
AU - Ni, Yuan
AU - Xie, Guotong
AU - Wang, Xiaoling
N1 - Publisher Copyright:
© 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - 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 Xu and Lapata (2020). 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.
AB - 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 Xu and Lapata (2020). 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.
UR - https://www.scopus.com/pages/publications/85123941346
M3 - 会议稿件
AN - SCOPUS:85123941346
T3 - Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021
SP - 96
EP - 102
BT - Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021
A2 - Demner-Fushman, Dina
A2 - Cohen, Kevin Bretonnel
A2 - Ananiadou, Sophia
A2 - Tsujii, Junichi
PB - Association for Computational Linguistics (ACL)
Y2 - 11 June 2021
ER -