Contextual embedding and model weighting by fusing domain knowledge on Biomedical Question Answering

TL;DR

This paper introduces a fusion approach combining open-domain and biomedical domain models with a weighting layer to improve biomedical question answering, achieving superior results on PubMed-based datasets.

Contribution

The paper presents a novel fusion method with model weighting for biomedical QA, leveraging domain-specific pre-training and unsupervised learning.

Findings

Outperforms state-of-the-art on BioMRC dataset

Effective fusion of open-domain and biomedical models

Model weighting improves answer accuracy

Abstract

Biomedical Question Answering aims to obtain an answer to the given question from the biomedical domain. Due to its high requirement of biomedical domain knowledge, it is difficult for the model to learn domain knowledge from limited training data. We propose a contextual embedding method that combines open-domain QA model \aoa and \biobert model pre-trained on biomedical domain data. We adopt unsupervised pre-training on large biomedical corpus and supervised fine-tuning on biomedical question answering dataset. Additionally, we adopt an MLP-based model weighting layer to automatically exploit the advantages of two models to provide the correct answer. The public dataset \biomrc constructed from PubMed corpus is used to evaluate our method. Experimental results show that our model outperforms state-of-the-art system by a large margin.