Publication: KU_ai at MEDIQA 2019: domain-specific pre-training and transfer learning for medical NLI
Files
Program
KU-Authors
KU Authors
Co-Authors
Publication Date
Language
Embargo Status
NO
Journal Title
Journal ISSN
Volume Title
Alternative Title
Abstract
In this paper, we describe our system and results submitted for the Natural Language Inference (NLI) track of the MEDIQA 2019 Shared Task (Ben Abacha et al., 2019). As KU ai team, we used BERT (Devlin et al., 2018) as our baseline model and pre-processed the MedNLI dataset to mitigate the negative impact of de-identification artifacts. Moreover, we investigated different pre-training and transfer learning approaches to improve the performance. We show that pre-training the language model on rich biomedical corpora has a significant effect in teaching the model domain-specific language. In addition, training the model on large NLI datasets such as MultiNLI and SNLI helps in learning task-specific reasoning. Finally, we ensembled our highest-performing models, and achieved 84.7% accuracy on the unseen test dataset and ranked 10th out of 17 teams in the official results.
Source
Publisher
Association for Computational Linguistics (ACL)
Subject
Computer science, artificial intelligence, Medical informatics
Citation
Has Part
Source
Proceedings of the BioNLP 2019 Workshop
Book Series Title
Edition
DOI
10.18653/v1/W19-5045