基于卷积神经网络的医学实体关系分类模型研究  

Classification Model for Medical Entity Relations with Convolutional Neural Network

作　　者：范少萍[1] 赵雨宣 安新颖[1] 吴清强[3] Fan Shaoping;Zhao Yuxuan;An Xinying;Wu Qingqiang(Institute of Medical Information/Medical Library,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100020,China;School of Finance,Central University of Finance and Economics,Beijing 102206,China;School of Informatics,Xiamen University,Xiamen 361005,China)

机构地区：[1]中国医学科学院/北京协和医学院医学信息研究所/图书馆,北京100020 [2]中央财经大学金融学院,北京102206 [3]厦门大学信息学院,厦门361005

出　　处：《数据分析与知识发现》2021年第9期75-84,共10页Data Analysis and Knowledge Discovery

基　　金：国家自然科学基金项目(项目编号:71704188);国家重点研发计划项目(项目编号:2016YFC0901902-2)的研究成果之一。

摘　　要：【目的】为提升关系分类模型性能,降低特征计算复杂性,提出一种融合多特征嵌入的卷积神经网络实体关系分类模型。【方法】参考已有研究的主要嵌入特征,提出融合位置和词汇级特征嵌入的卷积神经网络实体关系分类模型,并给出特征的计算表示方法,上述特征无需复杂计算算法,提高了模型性能。【结果】所提模型在生物医学领域语料库AIMed、GENIA和ChemProt上F1值分别为0.7342、0.9764和0.8900,在GENIA和ChemProt上实现了当前最佳性能。【局限】尚未融入生物医学领域先验知识等领域特色的特征。【结论】融合多特征嵌入的卷积神经网络实体关系分类模型具有良好的分类效果,可为生物医学领域关系抽取和知识库研究提供参考。[Objective]This paper proposes a new classification model for entity relationship based on the Convolutional Neural Network(CNN)with multi-features embedding,aiming to improve the classification results and simplify feature calculation.[Methods]Based on the existing algorithms of embedded features,our CNN model integrated word positions and lexical features,as well as demonstrated the representation methods for the features.These features did not require complex algorithm calculation,which improved the model’s performance.[Results]We examined the proposed model with the Bio-Medical corpus of AIMed,GENIA and ChemProt.The F1 scores were 0.7342,0.9764 and 0.8900,respectively.This model yielded the best results with the GENIA and ChemProt datasets.[Limitations]Our model did not include the prior domain knowledge from biomedical field.[Conclusions]The proposed model could effectively conduct entity relationship classification,which also help the research on relation extraction and knowledgebase construction in bio-medical field.

关 键 词：关系分类 卷积神经网络 位置特征 词汇级特征 

分 类 号：G350[文化科学—情报学]