文献类型：期刊文献

英文题名：Detecting Hypernymy Relations Between Medical Compound Entities Using a Hybrid-Attention Based Bi-GRU-CapsNet Model

作者：Xu, Chenming[1,3];Zhou, Yangming[1,2];Wang, Qi[2];Ma, Zhiyuan[2];Zhu, Yan[3]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[3]East China Univ Sci & Technol, Sch Sci, Shanghai 200237, Peoples R China

年份：2019

卷号：7

起止页码：175693

外文期刊名：IEEE ACCESS

收录：;EI(收录号：20195207922143);WOS:【SCI-EXPANDED(收录号:WOS:000509399500044)】；

基金：This work was supported in part by the National Key Research and Development Program of China for Precision Medical Research under Grant 2018YFC0910500, in part by the Shanghai Sailing Program under Grant 19YF1412400, in part by the Fundamental Research Funds for the Central Universities under Grant 222201817006, and in part by the National Major Scientific and Technological Special Project for Significant New Drugs Development under Grant 2018ZX09201008.

语种：英文

外文关键词：Capsule network; medical compound entities; electronic health records; hybrid attention mechanism; hypernymy detection

摘要：Named entities composed of multiple continuous words frequently occur in domain-specific knowledge graphs. In general, these named entities are composable and extensible, such as names of symptoms and diseases in the medical domain. Unlike the general entities, we address them as compound entities, and try to identify hypernymy relations between them. Hypernymy detection between compound entities plays a critical role in domain-specific knowledge graph construction. Traditional hypernymy detection approaches do not perform well on compound entities for two reasons. One is the lack of contextual information, and the other is the absence of compound entities, i.e. out-of-vocabulary (OOV) problem. In this paper, we propose a hybrid-attention-based method called Bi-GRU-CapsNet for the detection of hypernymy relations. The hybrid attention mechanism consists of heuristic attention and self-adaptive attention, which are used for the lack of contextual information. The attentions focus on the differences of two compound entities on the lexical and semantic level, respectively. For OOV problem, the English words or Chinese characters in compound entities are fed into bidirectional gated recurrent units (Bi-GRUs). Additionally, we use capsule network (CapsNet) to determine the existence of hypernymy relations under different cases. Experimental results show that our proposed method outperforms other baseline methods on both English and Chinese corpora of symptom and disease pairs.