基于本体特征的汽车领域命名实体识别  

An Ontology-Based Named Entity Recognition in Automotive Industry

作　　者：张永平[1] 朱艳辉[1] 朱道杰 王天吉[1] 李飞[1] ZHANG Yongping;ZHU Yanhui;ZHU Daojie;WANG Tianji;LI Fei(School of Computer,Hunan University of Technology,Zhuzhou Hunan 412007,China)

机构地区：[1]湖南工业大学计算机学院,湖南株洲412007

出　　处：《湖南工业大学学报》2016年第6期39-43,共5页Journal of Hunan University of Technology

基　　金：国家自然科学基金资助项目(61170102);国家社会科学基金资助项目(12BYY045);湖南省教育厅基金资助重点项目(15A049)

摘　　要：针对汽车领域命名实体识别中汽车属性名识别的准确率和召回率较低的问题,提出了一种基于本体特征的汽车领域命名实体识别方法。通过扩展现有叙词表,基于叙词表构建汽车领域本体,提取语料中的本体特征,利用CRFs模型对汽车领域命名实体进行识别。实验结果表明,本体特征能够有效地识别出汽车属性实体,准确率、召回率和F值分别为75.60%,66.12%和70.54%。In view of a low accuracy rate and recall rate of named entity recognition in the automotive industry,a new method of named entity recognition based on ontology has thus been proposed.By extending the existing thesauri,and constructing an automobile domain ontology,the ontology features are to be extracted from the corpus,and a named entity recognition based on a CRFs model can be achieved.The experimental results show that the ontology features can effectively identify the vehicle attribute entities,with its accuracy rate as high as75.60%,a recall rate as high as66.12%and a F-value as high as70.54%respectively.

关 键 词：命名实体识别 汽车领域 CRFS 本体 叙词表 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]