[1]潘理虎,赵彭彭,龚大立,等.煤矿事故案例命名实体识别方法研究[J].计算机技术与发展,2022,32(02):154-160.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 025]
　PAN Li-hu,ZHAO Peng-peng,GONG Da-li,et al.Combined ALBERT for Named Entity Recognition in Coal Mine Accident Cases[J].,2022,32(02):154-160.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 025]
点击复制

煤矿事故案例命名实体识别方法研究()

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

卷:
32
期数:
2022年02期
页码:
154-160
栏目:
应用前沿与综合
出版日期:
2022-02-10

文章信息/Info

Title:
Combined ALBERT for Named Entity Recognition in Coal Mine Accident Cases
文章编号:
1673-629X(2022)02-0154-07
作者:
潘理虎1 ; 赵彭彭1 ; 龚大立2 ; 闫慧敏3 ; 张英俊1
1. 太原科技大学 计算机科学与技术学院,山西 太原 030024;
2. 精英数智科技股份有限公司,山西 太原 030006;
3. 中国科学院 地理科学与资源研究所,北京 100101
Author(s):
PAN Li-hu1 ; ZHAO Peng-peng1 ; GONG Da-li2 ; YAN Hui-min3 ; ZHANG Ying-jun1
1. School of Computer Science and Technology,Taiyuan University of Science and Technology,Taiyuan 030024,China;
2. Jingying Shuzhi Technology Co. ,Ltd. ,Taiyuan 030006,China;
3. Institute of Geographic Science and Natural Resource Research,Chinese Academy of Sciences,Beijing 100101,China
关键词:
煤矿安全生产知识图谱; 命名实体识别; ALBERT; 迭代扩张卷积; Dropout; 自适应矩估计
Keywords:
knowledge graph of coal mine safety production; named entity recognition; ALBERT; iterative dilated convolution; Dropout; adaptive moment estimation
分类号:
TP391. 1
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 02. 025
摘要:
命名实体识别是自然语言处理的一项重要技术,也是问答系统、句法分析、机器翻译等下游工作的基本任务。 煤矿事故案例命名实体识别是构建煤矿安全生产知识图谱的关键环节,其效率和准确率直接影响后期知识图谱的质量。 针对传统命名实体识别方法训练时间长、识别率低的问题及煤矿事故案例的描述特点,以自构的标注语料集 CoalMineCorpus为研究对象,基于深度学习算法, 该文提出了一种结合 ALBERT 和迭代扩张卷积的命名实体识别方法。 首先引入ALBERT 预训练语言模型生成字向量,提升传统字向量的文本表示能力;然后将字向量序列输入改进的卷积神经网络中,其中卷积层采用四个三层结构的迭代扩张卷积模块完成特征抽取,采用 RELU 激活函数,取消池化层避免特征损失,使用Dropout 和自适应矩估计对模型进行优化;最后使用条件随机场对标签序列结果进行合法性约束。 实验结果表明,该模型在较大提升准确率、召回率和 F 值的同时可以有效缩短训练时间,可用于煤矿事故领域的命名实体识别工作。
Abstract:
Named entity recognition is an important technology in natural language processing,and also a basic task of downstream worksuch as question answering systems,syntax analysis,and machine translation. Named entity recognition of coal mine accident cases is akey link in the construction of the knowledge graph of coal mine safety production,and its efficiency and accuracy directly affect thequality of the later knowledge graph. Aiming at the problems of long training time and low recognition rate of traditional named entityrecognition methods and the description characteristics of coal mine accident cases,taking CoalMineCorpus,a self - constructed labeledcorpus,as the research object,based on deep learning algorithms,we propose a named entity recognition method based on ALBERT anditerative dilated convolution. Firstly,the ALBERT pre-training language model is introduced to generate word vectors to improve the textrepresentation ability of traditional word vectors. Then the word vector sequence is input into the improved convolutional neural network,where the convolution layer uses four three-layered iterative dilated convolution to complete feature extraction,uses the RELU activationfunction,cancels the pooling layer to avoid feature loss,uses Dropout and adaptive moment estimation to optimize the model. Finally,aconditional random field is used to restrict the validity of the label sequence results. The experiment shows that this model can effectivelyshorten? ?the training time while achieving a large improvement in accuracy, recall and F - value, which can be used for named entityrecognition in the field of coal mine accidents.

相似文献/References:

[1]陈 琛,刘小云,方玉华.融合注意力机制的电子病历命名实体识别[J].计算机技术与发展,2020,30(10):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 038]
　CHEN Chen,LIU Xiao-yun,FANG Yu-hua.Named Entity Recognition in Electronic Medical Record Introducing Attention Mechanisms[J].,2020,30(02):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 038]
[2]王卫红,吕红燕,曹玉辉,等.基于 BERT 的混合神经网络实体识别方法[J].计算机技术与发展,2021,31(08):100.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 017]
　WANG Wei-hong,LYU Hong-yan,CAO Yu-hui,et al.A Hybrid Neural Network Entity Recognition Method Based on BERT Model[J].,2021,31(02):100.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 017]
[3]王 俊,王修来*,栾伟先,等.基于 BERT 模型的科研人才领域命名实体识别[J].计算机技术与发展,2021,31(11):21.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 004]
　WANG Jun,WANG Xiu-lai*,LUAN Wei-xian,et al.Research on Named Entity Recognition of Scientific Research Talents Field Based on BERT Model[J].,2021,31(02):21.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 004]
[4]刘华玲,孙 毅.基于实体识别和信息融合的知识图谱研究[J].计算机技术与发展,2022,32(09):107.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 017]
　LIU Hua-ling,SUN Yi.Knowledge Graph Based on Entity Recognition and Information Fusion--A Case Study of COVID-19[J].,2022,32(02):107.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 017]
[5]孙安亮,时宏伟,王金策.基于字符与单词嵌入的航空安全命名实体识别[J].计算机技术与发展,2022,32(09):148.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 023]
　SUN An-liang,SHI Hong-wei,WANG Jin-ce.Named Entity Recognition Based on Character and Word Embedding in Aviation Safety[J].,2022,32(02):148.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 023]
[6]杜睿山,陈思路,刘文豪.基于岩石文本信息的命名实体识别[J].计算机技术与发展,2022,32(09):188.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 029]
　DU Rui-shan,CHEN Si-lu,LIU Wen-hao.Named Entity Recognition Based on Rock Text Information[J].,2022,32(02):188.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 029]
[7]胡慧婷,李建平,董振荣,等.基于 BERT 模型的教育技术学领域实体抽取[J].计算机技术与发展,2022,32(10):164.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 027]
　HU Hui-ting,LI Jian-ping,DONG Zhen-rong,et al.Named Entity Recognition Method in Educational Technology Field Based on BERT[J].,2022,32(02):164.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 027]
[8]罗 峦,夏骄雄.融合 ERNIE 与改进 Transformer 的中文 NER 模型[J].计算机技术与发展,2022,32(10):120.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 020]
　LUO Luan,XIA Jiao-xiong.Research on Chinese Named Entity Recognition Combining ERNIE with Improved Transformer[J].,2022,32(02):120.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 020]
[9]赵建强,朱万彤,陈 诚.基于多重卷积神经网络模型的命名实体识别[J].计算机技术与发展,2023,33(01):187.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 028]
　ZHAO Jian-qiang,ZHU Wan-tong,CHEN Cheng.Named Entity Recognition Based on Duplex Convolution Neural Network Model[J].,2023,33(02):187.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 028]
[10]贵向泉,郭 亮,李 立.基于 MRC 和 ERNIE 的有色冶金命名实体识别模型[J].计算机技术与发展,2023,33(10):93.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 015]
　GUI Xiang-quan,GUO Liang,LI Li.Nonferrous Metallurgical Named Entity Recognition Model Based on MRC and ERNIE[J].,2023,33(02):93.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 015]

更新日期/Last Update: 2022-02-10