%0 Generic %1 zhang2019enriching %A Zhang, Jiaying %A Zhang, Zhixing %A Zhang, Huanhuan %A Ma, Zhiyuan %A Zhou, Yangming %A He, Ping %D 2019 %K embedding graph knowledge medical proposal:bmbf2019 %T Enriching Medcial Terminology Knowledge Bases via Pre-trained Language Model and Graph Convolutional Network %U http://arxiv.org/abs/1909.00615 %X Enriching existing medical terminology knowledge bases (KBs) is an important and never-ending work for clinical research because new terminology alias may be continually added and standard terminologies may be newly renamed. In this paper, we propose a novel automatic terminology enriching approach to supplement a set of terminologies to KBs. Specifically, terminology and entity characters are first fed into pre-trained language model to obtain semantic embedding. The pre-trained model is used again to initialize the terminology and entity representations, then they are further embedded through graph convolutional network to gain structure embedding. Afterwards, both semantic and structure embeddings are combined to measure the relevancy between the terminology and the entity. Finally, the optimal alignment is achieved based on the order of relevancy between the terminology and all the entities in the KB. Experimental results on clinical indicator terminology KB, collected from 38 top-class hospitals of Shanghai Hospital Development Center, show that our proposed approach outperforms baseline methods and can effectively enrich the KB.

@misc{zhang2019enriching, abstract = {Enriching existing medical terminology knowledge bases (KBs) is an important and never-ending work for clinical research because new terminology alias may be continually added and standard terminologies may be newly renamed. In this paper, we propose a novel automatic terminology enriching approach to supplement a set of terminologies to KBs. Specifically, terminology and entity characters are first fed into pre-trained language model to obtain semantic embedding. The pre-trained model is used again to initialize the terminology and entity representations, then they are further embedded through graph convolutional network to gain structure embedding. Afterwards, both semantic and structure embeddings are combined to measure the relevancy between the terminology and the entity. Finally, the optimal alignment is achieved based on the order of relevancy between the terminology and all the entities in the KB. Experimental results on clinical indicator terminology KB, collected from 38 top-class hospitals of Shanghai Hospital Development Center, show that our proposed approach outperforms baseline methods and can effectively enrich the KB.}, added-at = {2019-10-22T21:35:01.000+0200}, author = {Zhang, Jiaying and Zhang, Zhixing and Zhang, Huanhuan and Ma, Zhiyuan and Zhou, Yangming and He, Ping}, biburl = {https://www.bibsonomy.org/bibtex/2220e6819ed8ead68d4be4d484aea4605/nosebrain}, interhash = {15b2768194a47cb544356816388183ef}, intrahash = {220e6819ed8ead68d4be4d484aea4605}, keywords = {embedding graph knowledge medical proposal:bmbf2019}, note = {cite arxiv:1909.00615Comment: 8 pages, submitted to BIBM 2019}, timestamp = {2019-10-22T21:35:01.000+0200}, title = {Enriching Medcial Terminology Knowledge Bases via Pre-trained Language Model and Graph Convolutional Network}, url = {http://arxiv.org/abs/1909.00615}, year = 2019 }