点击次数：

论文类型：期刊论文

发表时间：2019-05-21

发表刊物：BMC BIOINFORMATICS

收录刊物：SCIE、SSCI、PubMed、EI

卷号：20

期号：1

页面范围：260

ISSN号：1471-2105

关键字：CDR extraction; Gating units; Attention mechanism; Knowledge representations; Context features

摘要：Background: Automatic extraction of chemical-disease relations (CDR) from unstructured text is of essential importance for disease treatment and drug development. Meanwhile, biomedical experts have built many highly-structured knowledge bases (KBs), which contain prior knowledge about chemicals and diseases. Prior knowledge provides strong support for CDR extraction. How to make full use of it is worth studying.
   Results: This paper proposes a novel model called "Knowledge-guided Convolutional Networks (KCN)" to leverage prior knowledge for CDR extraction. The proposed model first learns knowledge representations including entity embeddings and relation embeddings from KBs. Then, entity embeddings are used to control the propagation of context features towards a chemical-disease pair with gated convolutions. After that, relation embeddings are employed to further capture the weighted context features by a shared attention pooling. Finally, the weighted context features containing additional knowledge information are used for CDR extraction. Experiments on the BioCreative V CDR dataset show that the proposed KCN achieves 71.28% F1-score, which outperforms most of the state-of-the-art systems.
   Conclusions: This paper proposes a novel CDR extraction model KCN to make full use of prior knowledge. Experimental results demonstrate that KCN could effectively integrate prior knowledge and contexts for the performance improvement.