融合双向GRU与注意力机制的医疗实体关系识别

doi:10.19678/j.issn.1000-3428.0054431

摘要/Abstract

摘要： 传统的实体关系识别方法多数是以单个句子作为处理单元，难以解决训练语料中实体关系标签标注错误的问题，且没有充分利用包含实体信息的多个句子在分类实体关系时的相互增强作用。为此，提出一种双向门控循环单元（GRU）和双重注意力机制结合的中文电子病历医疗实体关系识别方法。构建BiGRU-Dual Attention模型，采用双向GRU学习字的上下文信息，以获取更细粒度的特征，通过引入字级注意力机制提高对关系识别起决定作用的字权重，同时利用句子级注意力机制从多个句子中获取可增强识别性能的特征，降低标注错误的句子对分类的影响。实验结果表明，与BiLSTM-Attention模型相比，该模型的F1值提高了3.97%，达到了82.17%。

关键词: 中文电子病历, 医疗实体关系抽取, 双向门控循环单元, 双重注意力机制, 深度学习

Abstract: Most of existing methods for entity relationship recognition take a single sentence as processing unit,and fail to address tagging errors of entity relationships in the training corpus.Also,they cannot make full use of the mutual reinforcement of multiple sentences that contain entity information in relationship recognition.Therefore,this paper proposes a recognition method based on bidirectional Gated Recurrent Unit(GRU) and dual attention mechanism for entity relationships of Chinese electronic medical records.This paper proposes a BiGRU-Dual Attention model,and uses bidirectional GRU to learn the context information of characters in order to obtain more fine-grained features.Then the character-level attention mechanism is introduced to improve the weight of the characters that are key to relation recognition.Also,the sentence-level attention mechanism is employed to capture the features that can enhance recognition performance from multiple sentences,so as to reduce the weight of mislabeled sentences.Experimental results show that compared with the mainstream BiLSTM-Attention model,the proposed model increases the F1 value by 3.97% to 82.17%.

Key words: Chinese Electronic Medical Records(EMR), medical entity relation extraction, bidirectional Gated Recurrent Unit(GRU), dual attention mechanism, deep learning

中图分类号:

TP391

张志昌, 周侗, 张瑞芳, 张敏钰. 融合双向GRU与注意力机制的医疗实体关系识别[J]. 计算机工程, 2020, 46(6): 296-302.

ZHANG Zhichang, ZHOU Tong, ZHANG Ruifang, ZHANG Minyu. Medical Entity Relation Recognition Combining Bidirectional GRU and Attention[J]. Computer Engineering, 2020, 46(6): 296-302.

https://www.ecice06.com/CN/Y2020/V46/I6/296

图/表 9

20200617091908

20200617091912

20200617091915

20200617091918

20200617091921

20200617091924

20200617091927

20200617091930

20200617091933

参考文献

[1] Ministry of Health of the People's Republic of China.Basic standards for electronic medical records (trial)[J].China Health Quality Management,2010(4):13-14.(in Chinese)中华人民共和国卫生部.电子病历基本规范(试行)[J].中国卫生质量管理,2010(4):13-14.
[2] SHEN Wei.The change of medical behavior caused by the electronic medical record[J].Journal of Medical Informatics,2007,28(4):346-347.(in Chinese)沈伟.电子病历给医疗行为带来的变革[J].医学信息学杂志,2007,28(4):346-347.
[3] ZHANG Xiumei,XU Jianwu,CHENG Yuhua,et al.Knowledge-based building of a clinical decision support system[J].Chinese Journal of Hospital Administration,2014,30(6):472-475.(in Chinese)张秀梅,徐建武,程煜华,等.基于知识库的临床决策支持系统构建[J].中华医院管理杂志,2014,30(6):472-475.
[4] GRISHMAN R,SUNDHEIM B.Message understanding conference-6:a brief history[C]//Proceedings of the 16th Conference on Computational Linguistics.New York,USA:ACM Press,1996:466-471.
[5] UZUNER Ö,SOUTH B,SHEN S Y,et al.2010 i2b2/VA challenge on concepts,assertions,and relations in clinical text[J].Journal of the American Medical Informatics Association,2011,18(5):552-556.
[6] SARAWAGI S.Information extraction[J].Foundations and Trends in Databases,2008,1(3):261-377.
[7] ZHOU Jing.Chinese entity relation extraction based on conditional random fields model[J].Computer Engineering,2010,36(24):192-194.(in Chinese)周晶.基于条件随机域模型的中文实体关系抽取[J].计算机工程,2010,36(24):192-194.
[8] CHEN H H,DING Y W,TSAI S C,et al.Description of the NTU system used for MET-2[C]//Proceedings of the 7th Message Understanding Conference.San Diego,USA:Internet Society,1998:1-9.
[9] ZHANG Zhu.Weakly-supervised relation classification for information extraction[C]//Proceedings of the 13th ACM Conference on Information and Knowledge Management.New York,USA:ACM Press,2004:581-588.
[10] MINTZ M,BILLS S,SNOW R,et al.Distant supervision for relation extraction without labeled data[C]//Proceedings of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP.New York,USA:ACM Press,2009:1003-1011.
[11] RICHARD S,BRODY H,CHRISTOPHER D,et al.Semantic compositionality through recursive matrix-vector space[C]//Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.New York,USA:ACM Press,2012:1201-1211.
[12] ZENG Daojian,LIU Kang,LAI Siwei,et al.Relation classification via convolutional deep neural network[C]//Proceedings of the 25th International Conference on Computational Linguistics.Dubin,Ireland:[s.n.],2014:2335-2344.
[13] SUN Ziyang,GU Junzhong,YANG Jing.Chinese entity relation extraction method based on deep learning[J].Computer Engineering,2018,44(9):164-170.(in Chinese)孙紫阳,顾君忠,杨静.基于深度学习的中文实体关系抽取方法[J].计算机工程,2018,44(9):164-170.
[14] RINK B,HARABAGIU S,ROBERTS K.Automatic extraction of relations between medical concepts in clinical texts[J].Journal of the American Medical Informatics Association,2011,18(5):594-600.
[15] FANG Y C,HUANG H C,CHEN H H,et al.TCMGeneDIT:a database for associated traditional Chinese medicine,gene and disease information using text mining[J].BMC Complementary and Alternative Medicine,2008,8(1):58-58.
[16] WANG X Y,CHUSED A,ELHADAD N,et al.Automated knowledge acquisition from clinical narrative reports[C]//Proceedings of the American Medical Informatics Association.New York,USA:ACM Press,2008:783-787.
[17] HUANG Degen,JIANG Zhenchao,ZOU Li,et al.Drug-drug interaction extraction from biomedical literature using support vector machine and long short term memory networks[J].Information Sciences,2017(415/416):100-109.
[18] RINK B,HARABAGIU S.UTD:classifying semantic relations by combining lexical and semantic resources[C]//Proceedings of the 5th International Workshop on Semantic Evaluation.New York,USA:ACM Press,2010:256-259.
[19] SAHU S K,ANAND A,ORUGANTY K,et al.Relation extraction from clinical texts using domain invariant convolutional neural network[C]//Proceedings of the 15th Workshop on Biomedical Natural Language.Berlin,Germany:Springer,2016:206-215.
[20] LI Lingfeng,NIE Yuanping,HAN Weihong,et al.A multi-attention-based bidirectional long short-term memory network for relation extraction[C]//Proceedings of the International Conference on Neural Information.Berlin,Germany:Springer,2017:216-227.

选择文件类型/文献管理软件名称

选择包含的内容