[1]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):187-192.[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(01):187-192.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 028]
点击复制

基于多重卷积神经网络模型的命名实体识别()
分享到：

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

卷:
33
期数:
2023年01期
页码:
187-192
栏目:
人工智能
出版日期:
2023-01-10

文章信息/Info

Title:
Named Entity Recognition Based on Duplex Convolution Neural Network Model
文章编号:
1673-629X(2023)01--0187-06
作者:
赵建强1 ; 朱万彤2 ; 陈 诚1
1. 厦门市美亚柏科信息股份有限公司,福建 厦门 361008;
2. 西安电子科技大学 计算机科学与技术学院,陕西 西安 710071
Author(s):
ZHAO Jian-qiang1 ; ZHU Wan-tong2 ; CHEN Cheng1
1. Xiamen Meiya Pico Information Co. ,Ltd. ,Xiamen 361008,China;
2. School of Computer Science and Technology,Xidian University,Xi’an 710071,China
关键词:
命名实体识别; BERT; 卷积神经网络; 膨胀卷积; 自注意力机制
Keywords:
named entity recognition; BERT; convolutional neural network; dilated convolution; self-attention mechanism
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 01. 028
摘要:
针对命名实体识别任务,该文以可通过参数调节感受野范围的 IDCNN 为基础,提出了 BERT-Duplex CNN-SelfAttention-CRF 模型,在不引入其他辅助特征的条件下,采用 BERT 预训练模型来提供具有丰富语义信息的字嵌入,将字嵌入分别输入 IDCNN 和 CNN 中进行特征提取。 IDCNN 在提取长距离语义信息的前提下可以充分利用 GPU 的并行能力,CNN 在不损失并行能力的前提下可以弥补 IDCNN 对于局部上下文信息的缺失,将提取到的特征融合,通过引入自注意力机制在众多特征中选取对命名实体识别更有效的特征,最后通过 CRF 层提升实体标签预测的准确性。 为验证模型的有效性,该文在常用的 MSRA 数据集以及 Resume 数据集上进行实验,实验结果表明:该模型在 MSRA、Resume 数据集上,结果超越了 Lattice LSTM、BERT-Tagger、LR-CNN、PLET 等几个目前较优模型,相对于结果最好的 PLET 模型,该模型的 F1值分别提高了 1. 28 百分点、0. 15 百分点。
Abstract:
For the task of named entity recognition,we present BERT-Duplex CNN-Self Attention-CRF model based on IDCNN,whichcan adjust the receptive field range through parameters. Without introducing other auxiliary features,the BERT pre - training model isused to provide word embedding with rich semantic information,and the word embedding is input into IDCNN and CNN respectively forfeature extraction. IDCNN can make full use of the parallel ability of GPU on the premise of extracting long - distance semanticinformation. Meanwhile,CNN can make up for IDCNN爷 s lack of local context information without losing parallel ability. The self -attention mechanism can be used to select the feature which is more effective for named entity recognition task,next. Finally,the CRFlayer is used to improve the accuracy of entity label prediction. Experiments are carried out on MSRA dataset and Resume dataset. TheF1-score of the model on MSRA and Resume datasets are improved respectively than several current better models such as LatticeLSTM,BERT Tagger,LR-CNN and PLET,with 1. 28% 、0. 15% increased than the best baseline.

相似文献/References:

[1]王珊珊,邹 佳,程 序,等.GSGD:一种基于 BERT 与本体推理的自动分级系统[J].计算机技术与发展,2020,30(08):97.[doi:10. 3969 / j. issn. 1673-629X. 2020. 08. 016]
　WANG Shan-shan,ZOU Jia,CHENG Xu,et al.An Automatic Grading System Based on BERT and Ontology Reasoning[J].,2020,30(01):97.[doi:10. 3969 / j. issn. 1673-629X. 2020. 08. 016]
[2]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(01):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 038]
[3]黄东晋,耿晓云,李 娜,等.基于混合特征的电影评分预测系统[J].计算机技术与发展,2020,30(12):136.[doi:10. 3969 / j. issn. 1673-629X. 2020. 12. 024]
　HUANG Dong-jin,GENG Xiao-yun,LI Na,et al.Film Rating Prediction System Based on Mixed Features[J].,2020,30(01):136.[doi:10. 3969 / j. issn. 1673-629X. 2020. 12. 024]
[4]何 涛,陈 剑,闻英友,等.基于堆叠模型的司法短文本多标签分类[J].计算机技术与发展,2021,31(03):27.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 005]
　HE Tao,CHEN Jian,WEN Ying-you,et al.Multi-label Classification of Judicial Short Texts Based on Stacking Model[J].,2021,31(01):27.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 005]
[5]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(01):100.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 017]
[6]蔡玉舒,曹 扬,江 维,等.基于 BERT 的端到端旅游评论意见挖掘方法[J].计算机技术与发展,2021,31(09):118.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 020]
　CAI Yu-shu,CAO Yang,JIANG Wei,et al.End to End Opinion Mining Method Based on BERT for Tourism Comments[J].,2021,31(01):118.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 020]
[7]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(01):21.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 004]
[8]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.[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(01):154.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 025]
[9]龚汝鑫,余肖生.基于 BERT-BILSTM 的医疗文本关系提取方法[J].计算机技术与发展,2022,32(04):186.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 032]
　GONG Ru-xin,YU Xiao-sheng.Relation Extraction Method of Medical Texts Based on BERT-BILSTM[J].,2022,32(01):186.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 032]
[10]苏魁麟,张 凯,吕学强,等.基于融合模型的名词隐喻识别[J].计算机技术与发展,2022,32(06):192.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 032]
　SU Kui-lin,ZHANG Kai,LYU Xue-qiang,et al.Noun Metaphor Recognition Based on Fusion Model[J].,2022,32(01):192.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 032]
[11]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(01):107.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 017]
[12]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(01):164.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 027]

更新日期/Last Update: 2023-01-10