融合卷积神经网络和重启随机游走的实体链接方法  

An Entity Discover and Linking Approach Based on Convolutional Neural Network and Random Walk with Restart

作　　者：谭咏梅[1] 李晓光[1] 吕学强[2] TAN Yong-mei1, LI Xiao-guang1 , LU Xue-qiang2(1. Intelligence Science and Technology Center, Beijing University of Posts and Telecommunications, Beijing 100876, China; 2. Beijing Key Laboratory of Intemet Culture and Digital Dissemination Research, Beijing Information Science anti Technology University, Beijing 100101, Chin)

机构地区：[1]北京邮电大学智能科学与技术中心,北京100876 [2]北京信息科技大学网络文化与数字传播北京市重点实验室,北京100101

出　　处：《北京邮电大学学报》2018年第1期65-69,共5页Journal of Beijing University of Posts and Telecommunications

基　　金：国家自然科学基金面上项目(61671070);网络文化与数字传播北京市重点实验室开放课题项目(ICDD201703)

摘　　要：提出了一种融合卷积神经网络和重启随机游走的实体链接方法.该方法首先对文本中的指称进行识别,然后生成指称的候选实体集,随后使用融合卷积神经网络和重启随机游走的实体链接方法对候选实体进行选择,最后对在知识库中无对应实体的指称进行聚类.该方法在TAC-KBP2016的实体识别与链接评测数据集上的FCEAFm值为0.652,2016年评测第1名的FCEAFm为0.643,实验结果表明,使用融合卷积神经网络和重启随机游走的实体链接方法能够有效地进行实体链接.An entity linking approach based on convolutional neural network and random walk with restart was presented. This method first discovers the mentions in the text,after generates the mention candidate entity set,then selects the candidate entity using the entity linking approach based on convolutional neural network and random walk with restart and clusters the mentions those do not have the corresponding entity in the knowledge base. Our method FCEAFmis 0. 652 on the TAC-KBP2016 entity discovery and linking evaluation data set,and the first team is 0. 643. The results show our method can effectively solve this problem.

关 键 词：实体链接 卷积神经网络 重启随机游走 

分 类 号：TN911.22[电子电信—通信与信息系统]