The recent success of question answering systems is largely attributed to pre-trained language models. However, as language models are mostly pre-trained on general domain corpora such as Wikipedia, they often have difficulty in understanding biomedical questions. In this paper, we investigate the performance of BioBERT, a pre-trained biomedical language model, in answering biomedical questions including factoid, list, and yes/no type questions. BioBERT uses almost the same structure across various question types and achieved the best performance in the 7th BioASQ Challenge (Task 7b, Phase B). BioBERT pre-trained on SQuAD or SQuAD 2.0 easily outperformed previous state-of-the-art models. BioBERT obtains the best performance when it uses the appropriate pre-/post-processing strategies for questions, passages, and answers.
@article{arxiv.1909.08229,
title = {Pre-trained Language Model for Biomedical Question Answering},
author = {Wonjin Yoon and Jinhyuk Lee and Donghyeon Kim and Minbyul Jeong and Jaewoo Kang},
journal= {arXiv preprint arXiv:1909.08229},
year = {2019}
}
Comments
This paper is accepted for an oral presentation in BioASQ Workshop @ ECML PKDD 2019