WTMED at MEDIQA 2019: A Hybrid Approach to Biomedical Natural Language Inference

Zhaofeng Wu, Yan Song, Sicong Huang, Yuanhe Tian, Fei Xia

[How to correct problems with metadata yourself]

Abstract
Natural language inference (NLI) is challenging, especially when it is applied to technical domains such as biomedical settings. In this paper, we propose a hybrid approach to biomedical NLI where different types of information are exploited for this task. Our base model includes a pre-trained text encoder as the core component, and a syntax encoder and a feature encoder to capture syntactic and domain-specific information. Then we combine the output of different base models to form more powerful ensemble models. Finally, we design two conflict resolution strategies when the test data contain multiple (premise, hypothesis) pairs with the same premise. We train our models on the MedNLI dataset, yielding the best performance on the test set of the MEDIQA 2019 Task 1.
Anthology ID:
W19-5044
Volume:
Proceedings of the 18th BioNLP Workshop and Shared Task
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Dina Demner-Fushman, Kevin Bretonnel Cohen, Sophia Ananiadou, Junichi Tsujii
Venue:
BioNLP
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
415–426
Language:
URL:
https://aclanthology.org/W19-5044
DOI:
10.18653/v1/W19-5044
Bibkey:
Cite (ACL):
Zhaofeng Wu, Yan Song, Sicong Huang, Yuanhe Tian, and Fei Xia. 2019. WTMED at MEDIQA 2019: A Hybrid Approach to Biomedical Natural Language Inference. In Proceedings of the 18th BioNLP Workshop and Shared Task, pages 415–426, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
WTMED at MEDIQA 2019: A Hybrid Approach to Biomedical Natural Language Inference (Wu et al., BioNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/W19-5044.pdf
Code
 ZhaofengWu/MEDIQA_WTMED
Data
GLUE, MIMIC-III
PDF Search Code