[1]毛宏亮,艾孜尔古丽,陈德刚.基于多头注意力的电网调度领域命名实体识别[J].计算机技术与发展,2023,33(02):181-186.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 027]
　MAO Hong-liang,Azragul,CHEN De-gang.Named Entity Recognition in Grid Dispatch Domain Based on Multi-headed Attention[J].,2023,33(02):181-186.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 027]
点击复制

基于多头注意力的电网调度领域命名实体识别()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年02期
页码:
181-186
栏目:
人工智能
出版日期:
2023-02-10

文章信息/Info

Title:
Named Entity Recognition in Grid Dispatch Domain Based on Multi-headed Attention
文章编号:
1673-629X(2023)02-0181-06
作者:
毛宏亮1 ; 艾孜尔古丽1; 2 ; 陈德刚1
1. 新疆师范大学 计算机科学技术学院,新疆 乌鲁木齐 830054;
2. 国家语言资源监测与研究少数民族语言中心,新疆 乌鲁木齐 830000
Author(s):
MAO Hong-liang1 ; Azragul1; 2 ; CHEN De-gang1
1. School of Computer Science and Technology,Xinjiang Normal University,Urumqi 830054,China;
2. National Center for Language Resources Monitoring and Research on Minority Languages,Urumqi 830000,China
关键词:
实体识别; 电网调度; 多头注意力; 双向长短时记忆; 联合概率; 知识图谱
Keywords:
named entity recognition; grid dispatch; multi-headed attention; BiLSTM; joint probability; knowledge graph
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 02. 027
摘要:
针对电网调度领域实体识别准确率较低的问题,提出一种融合多头注意力机制和双向长短时记忆网络的电网调度领域中文命名实体识别方法。 利用词向量表示电网调度语音识别后语句,并将生成的词向量序列输入双向长短时记忆网络(BiLSTM) 挖掘其上下文语义特征,引入多头注意力机制重点关注文本中的实体词,挖掘其隐藏特征,同时通过条件随机场( CRF) 计算序列标签的联合概率标注出实体识别结果。 根据电网调度语音识别后文本特点自建标注数据集,并将电网调度语音识别文本中的命名实体细粒度划分为参数、设备、操作、系统、组织 5 个类别进行实验。 其结果表明,该方法对电网调度领域实体识别具有更高的准确率和召回率,且 F1 值可达到 93. 63% ,切实解决了电网调度领域实体识别任务中标注数据稀少和精度较低的问题,有助于电网调度领域知识图谱的构建。
Abstract:
To address the problem of low accuracy of entity recognition in the field of grid dispatching,a Chinese named entity recognitionmethod for grid dispatch domain 　that integrates multi-headed attention and BiLSTM is proposed. A word vector is used to represent thepost-recognition utterance of grid dispatch speech,and the generated word vector sequence is fed into BiLSTM to mine its contextualsemantic features,and a multi-headed attention is introduced to focus on the entity words in the text to mine its hidden features,while theentity recognition results are labeled by calculating the joint probability of sequence labels through CRF. Build an　notated datasetaccording to the text features after grid dispatch speech recognition,and fine-grainedly divide the entities contained in the grid dispatchspeech text into five categories: parameter,device,operation,system,and organization for experiments. It is showed that the proposedmethod has higher accuracy and recall rate, with F1 value of 93. 63% for entity recognition of grid dispatching domain, which caneffectively solve the problems of sparse annotation data and low accuracy in the entity recognition task in the field of grid dispatching,helpful to the construction of knowledge graph in the field of grid dispatching.

相似文献/References:

[1]王俊 胡燕.电力操作票在线自动生成系统的设计与实现[J].计算机技术与发展,2007,(05):89.
　WANG Jun,HU Yan.Design and Realization of Automatic Online Formation System of Switching Sequences Ticket for Power System[J].,2007,(02):89.
[2]赵震,张龙昌. XML文档实体识别技术研究[J].计算机技术与发展,2014,24(10):84.
　ZHAO Zhen,ZHANG Long-chang. Research on Entity Identification Technology on XML Documents[J].,2014,24(02):84.
[3]赵君珂,张振宇,蔡开裕.基于自然语言处理的医学实体识别与标签提取[J].计算机技术与发展,2019,29(09):18.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 004]
　ZHAO Jun-ke,ZHANG Zhen-yu,CAI Kai-yu.Medical Entity Recognition and Label Extraction Based on Natural Language Processing[J].,2019,29(02):18.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 004]
[4]彭 怀,宋井宽,唐向红.基于信息匹配方法的中文知识库问答系统[J].计算机技术与发展,2022,32(02):14.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 002]
　PENG Huai,SONG Jing-kuan,TANG Xiang-hong.Question Answering System of Chinese Knowledge Base Based on Information Matching Method[J].,2022,32(02):14.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 002]
[5]张 鑫,冼广铭*,梅灏洋,等.基于 Span 方法和多叉解码树的实体关系抽取[J].计算机技术与发展,2023,33(05):152.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 023]
　ZHANG Xin,XIAN Guang-ming*,MEI Hao-yang,et al.Entity Relation Extraction Based on Span Method and Multi-fork Decoding Tree[J].,2023,33(02):152.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 023]
[6]卜意磊,庞文迪,吴甜甜,等.面向食品监管领域的知识图谱构建研究[J].计算机技术与发展,2023,33(06):202.[doi:10. 3969 / j. issn. 1673-629X. 2023. 06. 030]
　BU Yi-lei,PANG Wen-di,WU Tian-tian,et al.Research on Knowledge Graph Construction for Food Supervision[J].,2023,33(02):202.[doi:10. 3969 / j. issn. 1673-629X. 2023. 06. 030]
[7]李正辉,廖光忠.基于多层次特征提取的中文医疗实体识别[J].计算机技术与发展,2023,33(09):119.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 018]
　LI Zheng-hui,LIAO Guang-zhong.Chinese Medical Entity Recognition Based on Multi-level Feature Extraction[J].,2023,33(02):119.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 018]

更新日期/Last Update: 2023-02-10