海量食品安全事件下的命名实体识别研究  

A research on identification of the named entity for large-scale food safety incidents

作　　者：徐飞[1,2] 宋英华 Xu Fei;Song Yinghua(China Research Center for Emergency Management, Wuhan University of Technology, Wuhan 430070, Hubei, China;School of Management, Wuhan University of Technology, Wuhan 430070, Hubei, China)

机构地区：[1]武汉理工大学中国应急管理研究中心,湖北武汉430070 [2]武汉理工大学管理学院,湖北武汉430070

出　　处：《科研管理》2018年第7期131-138,共8页Science Research Management

基　　金：国家社会科学基金重大项目:"基于情报流知识库的我国食品安全技术支撑体系优化策略研究"(15ZDB168)

摘　　要：对食品安全事件当中的实体进行分析和识别不仅有助于人们加深对食品安全事件的了解而且有利于管理者应对食品安全事件。基于食品安全事件语料库,通过系统地统计和分析人名和机构名的内部与外部特征,在制定的特征模板的基础上,基于条件随机场模型,本文完成了对机构名和人名这两类命名实体进行识别的任务。通过与最大熵模型的测试结果进行比较,实验表明条件随机场模型的整体性能比较突出,取得了较好的准确率和召回率,并说明基于条件随机场模型完全可以实现对食品安全事件文本当中实体的抽取。It is not only helpful for people to get a deeper understanding of food safety incident but also beneficial for managers to deal with food safety incidents and analyze and identify the named entity of food safety incidents. Based on food safety incident corpus and by counting and analyzing the internal and external characteristics of the entities of organization name and the person names, the identification task of the named entities of organization name and the person names in food safety incidents using con- ditional random field model is completed in formulating characteristics template. The overall performance of the conditional ran- dom field model is outstanding in the experimental results comparing with the test results of maximum entropy model, and the ac- curacy and recall rate is very well. The experiment states the entities extraction of food safety incident is completely feasible based on conditional random field model.

关 键 词：条件随机场模型 特征分析 实体识别 食品安全事件 

分 类 号：TS201.6[轻工技术与工程—食品科学]