期刊
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
卷 19, 期 4, 页码 2365-2376出版社
IEEE COMPUTER SOC
DOI: 10.1109/TCBB.2021.3079339
关键词
Task analysis; Biological system modeling; Knowledge discovery; Transfer learning; Bagging; Semantics; Natural language processing; Biomedical factoid question answering; transfer learning; name entity; question representation; ensemble
类别
资金
- State Key Laboratory, Software Development Environment of China [SKLSDE-2021ZX-16]
- National Natural Science Foundation of China [61977003]
Biomedical factoid question answering is a crucial task in biomedical question answering applications. This study proposes a framework that fine-tunes BioBERT with a named entity dataset to improve question answering performance. BiLSTM is applied to encode the question text for sentence-level information, and bagging is used to combine question and token level information for enhanced overall performance.
Biomedical factoid question answering is an important task in biomedical question answering applications. It has attracted much attention because of its reliability. In question answering systems, better representation of words is of great importance, and proper word embedding can significantly improve the performance of the system. With the success of pretrained models in general natural language processing tasks, pretrained models have been widely used in biomedical areas, and many pretrained model-based approaches have been proven effective in biomedical question-answering tasks. In addition to proper word embedding, name entities also provide important information for biomedical question answering. Inspired by the concept of transfer learning, in this study, we developed a mechanism to fine-tune BioBERT with a named entity dataset to improve the question answering performance. Furthermore, we applied BiLSTM to encode the question text to obtain sentence-level information. To better combine the question level and token level information, we use bagging to further improve the overall performance. The proposed framework was evaluated on BioASQ 6b and 7b datasets, and the results have shown that our proposed framework can outperform all baselines.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据