Knowledge-guided convolutional networks for chemical-disease relation extraction

BMC Bioinformatics

Shixian Ning¹  Huiwei Zhou¹  Zhuang Liu¹  Chengkun Lang¹  Yingyu Lin²  Lei Du³ 

[1] 0000 0000 9247 7930, grid.30055.33, School of Computer Science and Technology, Dalian University of Technology, Chuangxinyuan Building, No.2 Linggong Road, Ganjingzi District, 116024, Dalian, Liaoning, China;0000 0000 9247 7930, grid.30055.33, School of Foreign Languages, Dalian University of Technology, Arts Building, No.2 Linggong Road, Ganjingzi District, 116024, Dalian, Liaoning, China;0000 0000 9247 7930, grid.30055.33, School of Mathematical Sciences, Dalian University of Technology, Chuangxinyuan Building, No.2 Linggong Road, Ganjingzi District, 116024, Dalian, Liaoning, China;

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

DOI  :  10.1186/s12859-019-2873-7

来源: publisher

【 摘 要 】

BackgroundAutomatic 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.ResultsThis 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.ConclusionsThis 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.

【 授权许可】

CC BY