计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220200112-7.doi: 10.11896/jsjkx.220200112

• 人工智能 • 上一篇    下一篇

基于DCNN和GLU的武器领域实体关系抽取方法

李晗1, 侯守璐1, 佟强1,2, 谌彤童3, 杨启民1, 刘秀磊1,2   

  1. 1 北京信息科技大学数据与科学情报分析实验室 北京 100101;
    2 北京材料基因工程高精尖创新中心(北京信息科技大学) 北京 100101;
    3 北京跟踪与通信技术研究所 北京 100094
  • 出版日期:2023-06-10 发布日期:2023-06-12
  • 通讯作者: 刘秀磊(liuxiulei@bistu.edu.cn)
  • 作者简介:(yhlihan@126.com)
  • 基金资助:
    国家重点研发计划(2021YFB2600600);促进高校分类发展重点研究培育项目(2121YJPY225,2121YJPY226);北京信息科技大学校研基金项目;科研机构创新能力建设-数据科学与情报分析研究所

Entity Relation Extraction Method in Weapon Field Based on DCNN and GLU

LI Han1, HOU Shoulu1, TONG Qiang1,2, CHEN Tongtong3, YANG Qimin1, LIU Xiulei1,2   

  1. 1 Laboratory of Data Science and Information Studies,Beijing Information Science and Technology University,Beijing 100101,China;
    2 Beijing Advanced Innovation Center for Materials Genome Engineering,Beijing Information Science and Technology University,Beijing 100101,China;
    3 Beijing Institute of Tracking and Telecommunications Technology,Beijing 100094,China
  • Online:2023-06-10 Published:2023-06-12
  • About author:LI Han,born in 1997,postgraduate.Her main research interests include know-ledge graph and relation extraction,and so on. LIU Xiulei,born in 1981,Ph.D,professor,is a member of China Computer Federation.His main research interests include ontology matching,semantic sensor,knowledge graph,semantic Web and semantic search,and so on.
  • Supported by:
    National Key R&D Program of China(2021YFB2600600),Promoting the Classified Development of Universities-Key Research and Cultivation Projects(2121YJPY225,2121YJPY226),Natural Science Foundation of Beijing Information Science & Technology University and Innovation Capacity Building of Scientific Research Institutions-Institute of Data Science and Information Analysis.

PDF (PC)

563

摘要： 武器领域的非结构化文本数据通常十分复杂,单句内可能存在“一武器与多个武器相关联”或“两武器之间存在多种关系”等情况,为此提出基于膨胀卷积神经网络和门控线性单元的实体关系抽取方法以处理该类型数据中存在的关系重叠问题。该方法将拼接了词向量和位置向量的句子编码向量传入带有门控机制的膨胀卷积神经网络模型,引入可以快速抽取句内命名实体特征信息的自注意力机制,通过分层次的序列标注方式识别出句中全部实体以及每个主实体对应的所有关系和客实体,进而生成武器领域实体关系三元组。实验结果显示,该方法在自行标注的武器领域数据集上的F1值达81.1%,具备一定的实体关系抽取能力,在不同重叠类型下的F1值均高于78%,能够解决非结构化数据的关系重叠问题,同时在公开数据集NYT上也有良好的表现。

关键词: 关系抽取, 关系重叠, 膨胀卷积神经网络, 门控线性单元

Abstract: Unstructured text data in the field of weapons is usually very complex.In a single sentence,one weapon may be associated with multiple weapons or there may be multiple relations between two weapons.An entity relation extraction method based on dilated convolutional neural network and gated linear unit is proposed to solve the problem of overlapping relation in this type of data.This method introduces the sentence coding vector into the dilated convolutional neural network model with gated linear unit,which combines word vector and position vector.And it introduces the self-attention mechanism to extract the feature information of entities in sentences quickly.Through hierarchical sequence annotation,this model identifies all entities in the sentence and all relations and object entities corresponding to each subject entity,and generates the entity relation triplet in the field of weapons.The F1 value of this method on the self-labeled weapon field data set is 81.1%,and it has a certain entity relation extraction ability,according to the experimental results.The F1 value for various overlap types is greater than 78%,which solves the problem of unstructured data relation overlap.At the same time,it performs admirably on the NYT public data set.

Key words: Relation extraction, Overlapping relation, Dilated convolutional neural network, Gated linear unit

中图分类号: 

  • TP391
[1]ZENG X,ZENG D,HE S,et al.Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).Melbourne,Australia:Association for Computational Linguistics,2018:506-514.
[2]WEI Z,SU J,WANG Y,et al.A Novel Cascade Binary Tagging Framework for Relational Triple Extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2020:1476-1488.
[3]WANG Y,YU B,ZHANG Y,et al.TPLinker:Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking[J].arXiv:2010.13415,2020.
[4]XU J,ZHANG Z X,WU Z X.Review on Techniques of Entity Relation Extraction[J].New Technology of Library and Information Service,2008,24(8):18-23.
[5]CHEN H W,ZHANG X Y,WANG T.Research on Named Entity Recognition[J].Computer Science,2005,32(4):44-48.
[6]TRAN K M,BISK Y,VASWANI A,et al.Unsupervised Neural Hidden Markov Models[C]//Proceedings of the Workshop on Structured Prediction for NLP.2016:63-71.
[7]MA X,HOVY E.End-to-end Sequence Labeling via Bi-direc-tional LSTM-CNNs-CRF[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics(Vo-lume 1:Long Papers).Berlin,Association for Computational Linguistics,2016:1064-1074.
[8]LI X,SUN X,MENG Y,et al.Dice Loss for Data-imbalanced NLP Tasks[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2020:465-476.
[9]ZHONG Z,CHEN D.A Frustratingly Easy Approach for Entity and Relation Extraction[C]//Proceedings of the 2021 Confe-rence of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Association for Computational Linguistics,2021:50-61.
[10]LI X,FENG J,MENG Y,et al.A Unified MRC Framework for Named Entity Recognition[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2020:5849-5859.
[11]WANG X,JIANG Y,BACH N,et al.Automated Concatenation of Embeddings for Structured Prediction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing(Long Papers).Association for Computational Linguistics,2021:2643-2660.
[12]ZHOU W,CHEN M.Learning from Noisy Labels for Entity-Centric Information Extraction[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Proces-sing.Association for Computational Linguistics,2021:5381-5392.
[13]SCHWETER S,AKBIK A.FLERT:Document-Level Features for Named Entity Recognition[J].arXiv:2011.06993,2020.
[14]YE D,LIN Y,SUN M.Pack Together:Entity and Relation Extraction with Levitated Marker[J].arXiv:2109.06067,2021.
[15]E H H,ZHANG W J,XIAO S Q,et al.Survey of Entity Relationship Extraction Based on Deep Learning[J].Journal of Software,2019,30(6):1793-1818.
[16]SANTOS C N,XIANG B,ZHOU B.Classifying Relations byRanking with Convolutional Neural Networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing(Long Papers).Beijing:Association for Computational Linguistics,2015:626-634.
[17]WANG L,CAO Z,MELO G,et al.Relation Classification via Multi-Level Attention CNNs[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).Berlin:Association for ComputationalLinguistics,2016:1298-1307.
[18]WANG H,TAN M,YU M,et al.Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers[C]//Proceedings of the 57th Annual Meeting of the Association for ComputationalLinguistics.Florence:Association for Computational Linguistics,2019:1371-1377.
[19]COHEN A D,ROSENMAN S,GOLDBERG Y.Relation Classification as Two-way Span-Prediction[J].arXiv:2010.04829,2020.
[20]MIWA M,BANSAL M.End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).Berlin:Association for Computational Linguistics,2016:1105-1116.
[21]ZHENG S,WANG F,BAO H,et al.Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).Vancouver:Association for Computational Linguistics,2017:1227-1236.
[22]BEKOULIS G,DELEU J,DEMEESTER T,et al.Joint entity recognition and relation extraction as a multi-head selection problem[J].Expert Systems with Applications,2018,114:34-45.
[23]SUI D,CHEN Y,LIU K,et al.Joint Entity and Relation Extraction with Set Prediction Networks[J].arXiv:2011.01675,2020.
[24]HUGUET CABOT P L,NAVIGLI R.REBEL:Relation Extraction By End-to-end Language generation[C]//Findings of the Association for Computational Linguistics:EMNLP 2021.Punta Cana:Association for Computational Linguistics,2021:2370-2381.
[25]MIKOLOV T,CHEN K,CORRADO G,et al.Efficient Estima-tion of Word Representations in Vector Space[J].arXiv:1301.3781,2013.
[26]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isAll You Need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:6000-6010.
[27]RIEDEL S,YAO L,MCCALLUM A.Modeling Relations and Their Mentions without Labeled Text[C]//Machine Learning and Knowledge Discovery in Databases.Berlin:Springer,2010:148-163.
[28]FU T J,LI P H,MA W Y.GraphRel:Modeling Text as Relational Graphs for Joint Entity and Relation Extraction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.Florence:Association for Computational Linguistics,2019:1409-1418.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发