Hierarchical Representation-based Dynamic Reasoning Network for Biomedical Question Answering

Jianguo Mao, Jiyuan Zhang, Zengfeng Zeng, Weihua Peng, Wenbin Jiang, Xiangdong Wang, Hong Liu, Yajuan Lyu


Abstract
Recently, Biomedical Question Answering (BQA) has attracted growing attention due to its application value and technical challenges. Most existing works treat it as a semantic matching task that predicts answers by computing confidence among questions, options and evidence sentences, which is insufficient for scenarios that require complex reasoning based on a deep understanding of biomedical evidences. We propose a novel model termed Hierarchical Representation-based Dynamic Reasoning Network (HDRN) to tackle this problem. It first constructs the hierarchical representations for biomedical evidences to learn semantics within and among evidences. It then performs dynamic reasoning based on the hierarchical representations of evidences to solve complex biomedical problems. Against the existing state-of-the-art model, the proposed model significantly improves more than 4.5%, 3% and 1.3% on three mainstream BQA datasets, PubMedQA, MedQA-USMLE and NLPEC. The ablation study demonstrates the superiority of each improvement of our model. The code will be released after the paper is published.
Anthology ID:
2022.coling-1.127
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1480–1489
Language:
URL:
https://aclanthology.org/2022.coling-1.127
DOI:
Bibkey:
Cite (ACL):
Jianguo Mao, Jiyuan Zhang, Zengfeng Zeng, Weihua Peng, Wenbin Jiang, Xiangdong Wang, Hong Liu, and Yajuan Lyu. 2022. Hierarchical Representation-based Dynamic Reasoning Network for Biomedical Question Answering. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1480–1489, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Hierarchical Representation-based Dynamic Reasoning Network for Biomedical Question Answering (Mao et al., COLING 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2022.coling-1.127.pdf
Data
PubMedQA