导弹领域文本嵌套命名实体识别方法研究

doi:10.16182/j.issn1004731x.joss.22-0456

系统仿真学报 ›› 2023, Vol. 35 ›› Issue (8): 1757-1767.doi: 10.16182/j.issn1004731x.joss.22-0456

导弹领域文本嵌套命名实体识别方法研究

关景文¹(), 宋晓²(), 李晓庆³, 杨彤², 周军华³

^1. 北京航空航天大学自动化学院，北京 100191
^2. 北京航空航天大学网络空间安全学院，北京 100191
^3. 北京仿真中心，北京 100854

收稿日期:2022-05-06 修回日期:2022-09-04 出版日期:2023-08-25 发布日期:2023-08-15
作者简介:
关景文(1997-)，男，硕士，研究方向为知识图谱。E-mail： 1004141383@qq.com
基金资助:
国家重点研发计划(2020YFB1712203)

Research on Nested Named Entity Recognition in Missile Field Text

Jingwen Guan¹(), Xiao Song²(), Xiaoqing Li³, Tong Yang², Junhua Zhou³

^1. School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China
^2. School of Cyber Science and Technology, Beihang University, Beijing 100191, China
^3. Beijing Simulation Center, Beijing 100854, China

Received:2022-05-06 Revised:2022-09-04 Online:2023-08-25 Published:2023-08-15

摘要/Abstract

关键词: 导弹, 嵌套命名实体识别, 知识抽取, 机器阅读理解, 语言学特征

Key words: missile, nested named entity recognition, knowledge extraction, machine reading comprehension, linguistic features

关景文, 宋晓, 李晓庆, 杨彤, 周军华. 导弹领域文本嵌套命名实体识别方法研究[J]. 系统仿真学报, 2023, 35(8): 1757-1767.

Jingwen Guan, Xiao Song, Xiaoqing Li, Tong Yang, Junhua Zhou. Research on Nested Named Entity Recognition in Missile Field Text[J]. Journal of System Simulation, 2023, 35(8): 1757-1767.

图/表 11

图1

表1

图2

图4

图3

图5

表2

表3

表4

图6

表5

参考文献 19

1	杨伟凯, 王艳, 纪志成. 面向知识图谱的智能生产系统工艺知识推理方法[J]. 系统仿真学报, 2023, 35(4): 773-785.
	Yang Weikai, Wang Yan, Ji Zhicheng. Knowledge Graph-based Process Knowledge Reasoning Method for Intelligent Production System[J]. Journal of System Simulation, 2023, 35(4): 773-785.
2	顾丹阳, 李明倩, 权冀川, 等. 基于本体的主战武器装备知识图谱构建[J]. 指挥控制与仿真, 2021, 43(6): 14-20.
	Gu Danyang, Li Mingqian, Quan Jichuan, et al. Ontology Based Knowledge Graph Construction for Combat Weapon Equipment[J]. Command Control & Simulation, 2021, 43(6): 14-20.
3	焦凯楠, 李欣, 朱容辰. 中文领域命名实体识别综述[J]. 计算机工程与应用, 2021, 57(16): 1-15.
	Jiao Kainan, Li Xin, Zhu Rongchen. Overview of Chinese Domain Named Entity Recognition[J]. Computer Engineering and Applications, 2021, 57(16): 1-15.
4	刘浏, 王东波. 命名实体识别研究综述[J]. 情报学报, 2018, 37(3): 329-340.
	Liu Liu, Wang Dongbo. A Review on Named Entity Recognition[J]. Journal of the China Society for Scientific and Technical Information, 2018, 37(3): 329-340.
5	陈曙东, 欧阳小叶. 命名实体识别技术综述[J]. 无线电通信技术, 2020, 46(3): 251-260.
	Chen Shudong, Ouyang Xiaoye. Overview of Named Entity Recognition Technology[J]. Radio Communications Technology, 2020, 46(3): 251-260.
6	Huang Zhiheng, Xu Wei, Yu Kai. Bidirectional LSTM-CRF Models for Sequence Tagging[EB/OL]. (2015-08-09)[2022-04-27].
7	Devlin J, Chang Mingwei, Lee K, et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[EB/OL]. (2019-05-24)[2022-04-27].
8	Sohrab M G, Miwa M. Deep Exhaustive Model for Nested Named Entity Recognition[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: ACL, 2018: 2843-2849.
9	Zheng Changmeng, Cai Yi, Xu Jingyun, et al. A Boundary-aware Neural Model for Nested Named Entity Recognition[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Stroudsburg, PA, USA: ACL, 2019: 357-366.
10	Fisher J, Vlachos A. Merge and Label: A Novel Neural Network Architecture for Nested NER[EB/OL]. (2019-06-30)[2022-04-27].
11	Lin Hongyu, Lu Yaojie, Han Xianpei, et al. Sequence-to-nuggets: Nested Entity Mention Detection via Anchor-region Networks[EB/OL]. (2019-06-10)[2022-04-27].
12	Wang Bailin, Lu Wei, Wang Yu, et al. A Neural Transition-based Model for Nested Mention Recognition[EB/OL]. (2018-10-03)[2022-04-27].
13	Ju Meizhi, Miwa M, Ananiadou S. A Neural Layered Model for Nested Named Entity Recognition[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Stroudsburg, PA, USA: ACL, 2018: 1446-1459.
14	Sohrab M G, Miwa M. Deep Exhaustive Model for Nested Named Entity Recognition[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: ACL, 2018: 2843-2849.
15	Shibuya T, Hovy E. Nested Named Entity Recognition via Second-best Sequence Learning and Decoding[J]. Transactions of the Association for Computational Linguistics, 2020, 8: 605-620.
16	Li Xiaoya, Feng Jingrong, Meng Yuxian, et al. A Unified MRC Framework for Named Entity Recognition[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA, USA: ACL, 2020: 5849-5859.
17	黄昌宁, 李玉梅, 朱晓丹. 中文文本标注规范(5.0版)[EB/OL]. (2006-03-27)[2022-04-27].
	Huang Changning, Li Yumei, Zhu Xiaodan. Tokenization Guidelines of Chinese Text (V 5.0)[EB/OL]. (2006-03-27)[2022-04-27].
18	Liu Yinhan, Ott M, Goyal N, et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach[EB/OL]. (2019-07-26)[2022-04-27].
19	Dai Zhenjin, Wang Xutao, Ni Pin, et al. Named Entity Recognition Using BERT BiLSTM CRF for Chinese Electronic Health Records[C]//2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). Piscataway, NJ, USA: IEEE, 2019: 1-5.

统计量	值
总字数	409 224
总句数	3 581
总实体数	6 021
嵌套实体数	1 840
嵌套实体占比/%	30.56

	B-Model	I-Model	B-Object	I-Object	O
B-Model	0.43	0.81	0.04	0.07	0.36
I-Model	0.52	0.71	0.35	0.12	0.44
B-Object	0.45	0.21	0.63	0.73	0.50
I-Object	0.62	0.18	0.46	0.65	0.54
O	0.42	0.12	0.40	0.13	0.61
…	…	…	…	…	…

参数	值
学习率	3×10^-5
学习衰减率	0.01
学习算法	Adam
训练轮次	20
Batch size	8
Dropout值	0.1

实验方法	精确率	召回率	F1值
BiLSTM-CRF^[6]	0.503 4	0.501 9	0.502 6
Bert-BiLSTM-CRF^[7,19]	0.653 5	0.692 3	0.672 3
BERT-MRC^[16]	0.695 4	0.723 1	0.709 0
Roberta-BiLSTM-CRF^[18-19]	0.699 3	0.723 8	0.711 3
MRC-NER-LF	0.703 5	0.742 3	0.722 4

实体类型	精确率	召回率	F1值
Object	0.678 6	0.950 0	0.791 7
Model	0.688 9	0.584 9	0.632 7
Method	0.600 0	0.486 5	0.537 3
Parameter	0.605 3	0.500 0	0.547 6
Function	0.500 0	0.375 0	0.428 6
Behavior	0.500 0	0.277 8	0.357 1

导弹领域文本嵌套命名实体识别方法研究

Research on Nested Named Entity Recognition in Missile Field Text

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 19

相关文章 15

编辑推荐

Metrics

本文评价

实验方法	精确率	召回率	F1值
BERT-BiLSTM-CRF	0.573 4	0.351 5	0.435 8
Layered-BiLSTM-CRF	0.553 4	0.541 0	0.547 1
BERT-MRC	0.600 3	0.602 2	0.598 4
MRC-NER-LF	0.617 2	0.621 2	0.613 2

[1]	邵诚, 孙宏远, 张林. 基于PSO-LSSVM的反舰导弹自控弹道仿真[J]. 系统仿真学报, 2021, 33(4): 918-926.
[2]	史岩, 张立华, 董受全, 王珏. 基于ACO算法和Bezier曲线优化的巡航导弹航路规划[J]. 系统仿真学报, 2020, 32(1): 122-129.
[3]	阮开智, 袁晴晴, 翟文华, 张志强. 基于Xsim平台的防空导弹武器系统仿真平台设计[J]. 系统仿真学报, 2020, 32(1): 142-148.
[4]	吴帅, 周晓华, 汪莉莉, 姚行中. 基于实际采样的导弹弹道建模与仿真[J]. 系统仿真学报, 2019, 31(4): 811-817.
[5]	赵春博, 范军芳, 刘宁. 微小型制导弹药姿态解算方法仿真研究[J]. 系统仿真学报, 2019, 31(12): 2877-2884.
[6]	刘闻, 王晓路, 汪宏昇, 张恒, 王长庆. 基于Agent的低轨预警卫星星座探测仿真分析[J]. 系统仿真学报, 2019, 31(11): 2413-2421.
[7]	廖瑛, 季海雨, 薛高雄. 基于伪谱法的巡航导弹最优闭环制导方法[J]. 系统仿真学报, 2018, 30(9): 3464-3471.
[8]	孙杰, 王天云, 戴幻尧, 莫翠琼, 赵晶. 反舰导弹最近邻目标选择器搜捕性能仿真分析[J]. 系统仿真学报, 2018, 30(6): 2362-2367.
[9]	李龙跃, 刘付显, 赵慧珍. 弹道导弹防御M/M/N排队系统建模与仿真[J]. 系统仿真学报, 2018, 30(4): 1260-1271.
[10]	田浩, 穆洲, 李慧通, 赵阳. 导弹外头罩分离及落区预测仿真[J]. 系统仿真学报, 2018, 30(3): 1056-1062.
[11]	刘柏廷, 王晓雷, 王超磊, 陶渝辉, 杨召伟. 基于多散射中心模拟的导弹连射半实物仿真方法[J]. 系统仿真学报, 2018, 30(12): 4732-4737.
[12]	马飞, 吴云洁, 程明智. 基于自抗扰解耦的BTT导弹非奇异终端滑模控制[J]. 系统仿真学报, 2017, 29(9): 2175-2181.
[13]	孙志朋, 龚光红. 空射型反舰导弹虚拟飞行建模仿真[J]. 系统仿真学报, 2017, 29(10): 2567-2573.
[14]	彭明星, 吴云洁, 朱付涛. 反舰导弹编队飞行控制方法研究[J]. 系统仿真学报, 2017, 29(1): 212-217.
[15]	张重先, 李向林, 刘玉秋. 复杂外形导弹出水过程空化流数值计算研究[J]. 系统仿真学报, 2016, 28(6): 1321-1328.