摘要
在核电领域的知识管理过程中,需要使用命名实体识别技术抽取高质量语义实体,以进行核电领域文本的智能分析和处理。在现有研究的基础上,通过增强网络对上下文信息的提取能力,提升模型对嵌套命名实体的识别准确率。经实验验证,所提方法较现有方法在准确率与召回率指标上提升显著,与BiFlaG网络对比,准确率提高9.52%,召回率提高8.51%,F_(1)值提高9.02%。所提方法对嵌套命名实体识别优于BiFlaG等网络。
In the process of knowledge management in nuclear power,it’s necessary to use named entity recognition to extract high-quality semantic entities for intelligent analysis and processing of text in nuclear power.On the basis of existing research,the recognition precision rate of the model for nested named entities is improved by enhancing the ability of the network rate to extract context information.The experimental results show that the proposed method improves the precision and recall rate significantly compared with the existing methods.Compared with the BiFlaG network,the precision rate is increased by 9.52%,the recall rate is increased by 8.51%,and the F_(1) value is increased by 9.02%.
作者
荆鑫
王华峰
刘潜峰
罗嗣梧
张凡
JING Xin;WANG Huafeng;LIU Qianfeng;LUO Siwu;ZHANG Fan(School of Information Engineering,North China University of Technology,Beijing 100144,China;School of Software,Beihang University,Beijing 100191,China;Institute of Nuclear and New Entergy Technology,Tsinghua University,Beijing 100084,China;College of Software,Taiyuan University of Technology,Taiyuan 030024,China)
出处
《北京航空航天大学学报》
EI
CAS
CSCD
北大核心
2022年第12期2556-2565,共10页
Journal of Beijing University of Aeronautics and Astronautics
基金
北京市教育委员会科研计划(KM202110009001)
河北省科研计划(203777116D)。
关键词
命名实体识别
核电
双向语言模型
图卷积神经网络
自注意力机制
named entity recngnition
nuclear power
embeddings from language model
graph convolutional networks
self attention