双向循环进化的实体链接及知识推理框架

doi:10.12305/j.issn.1001-506X.2022.09.22

系统工程与电子技术 ›› 2022, Vol. 44 ›› Issue (9): 2878-2885.doi: 10.12305/j.issn.1001-506X.2022.09.22

双向循环进化的实体链接及知识推理框架

封皓君^1,*, 段立¹, 张碧莹¹, 刘海潮^1,²

1. 海军工程大学电子工程学院, 湖北武汉 430033
2. 中国人民解放军91202部队, 辽宁葫芦岛 125004

收稿日期:2021-06-23 出版日期:2022-09-01 发布日期:2022-09-09
通讯作者: 封皓君
作者简介:封皓君(1997—), 男, 硕士研究生, 主要研究方向为模式识别与智能系统、自然语言处理|段立(1976—), 男, 教授, 博士, 主要研究方向为军事知识工程、信息融合|张碧莹(1997—), 女, 硕士研究生, 主要研究方向为信息对抗、数据挖掘|刘海潮(1994—), 男, 硕士研究生, 主要研究方向为军事知识工程、军事指挥

Bidirectional cyclic evolutionary framework of entity linking and knowledge reasoning

Haojun FENG^1,*, Li DUAN¹, Biying ZHANG¹, Haichao LIU^1,²

1. College of Electronic Engineering, Naval University of Engineering, Wuhan 430033, China
2. Unit 91202 of the PLA, Huludao 125004, China

Received:2021-06-23 Online:2022-09-01 Published:2022-09-09
Contact: Haojun FENG

摘要/Abstract

摘要：

为体系化、智能化提升自然语言处理中实体链接任务的准确率, 同时解决图谱噪声混杂、关系稀疏等问题, 基于第三代人工智能知识&数据双轮驱动思想提出一种双向循环进化的实体链接与知识推理框架。基于知识图谱下的实体链接技术设计正向进化模块, 基于知识推理与元学习等技术设计反向进化模块, 多次循环双向控制过程实现两任务在弱监督下自我迭代和智能升级。实验表明, 在模块化设计加持下, 该框架可从特定领域文本习得特定领域知识, 并实现快速增量更新, 有效提升实体链接、知识推理效率; 同时兼具开放性, 为各业务领域小样本下文本分析能力的迭代升级提供新方法。

关键词: 自然语言处理, 实体链接, 知识推理, 双向控制, 模块化设计

Abstract:

To improve the accuracy of entity linking task in natural language processing in a systematic and intelligent way, and to solve the problems of hybrid graph noise and sparse relationship, a bidirectional cyclic evolutionary framework of entity linking and knowledge reasoning based on the knowledge & data two-wheel driving idea of the third-generation artificial intelligence is proposed. The forward evolution module is designed based on the entity linking technology under knowledge graph, and the reverse evolution module is designed based on the knowledge reasoning and new technologies such as meta-learning. The bidirectional control process is cycled several times to realize self-iteration and intelligent upgrading of two tasks under weak supervision. Experiments show that, with the help of modular design, the framework can acquire domain-specific knowledge from domain-specific texts and rapid incremental update, which can effectively improve the efficiency of entity linking and knowledge reasoning. It also provides a new method for iterative upgrading of text analysis capability under small samples in various fields.

Key words: natural language processing, entity linking, knowledge reasoning, bidirectional control, modular design

中图分类号:

TP391.1

封皓君, 段立, 张碧莹, 刘海潮. 双向循环进化的实体链接及知识推理框架[J]. 系统工程与电子技术, 2022, 44(9): 2878-2885.

Haojun FENG, Li DUAN, Biying ZHANG, Haichao LIU. Bidirectional cyclic evolutionary framework of entity linking and knowledge reasoning[J]. Systems Engineering and Electronics, 2022, 44(9): 2878-2885.

图/表 9

图1

图2

图3

图4

图5

图6

图7

图8

图9

参考文献 31

1	OLIVEIRA I L , FILETO R , SPECK R , et al. Towards holistic entity linking: survey and directions[J]. Information Systems, 2021, 95, 101624. doi: 10.1016/j.is.2020.101624
2	MYTHREI S , SINGARAVELAN S . Survey on entity linking for domain specific with heterogeneous information networks[J]. Informatologia, 2020, 53 (3/4): 173- 184.
3	马忠贵, 倪润宇, 余开航. 知识图谱的最新进展、关键技术和挑战[J]. 工程科学学报, 2020, 42 (10): 1254- 1266.
	MA Z G , NI R Y , YU K H . Recent advances, key technologies and challenges in knowledge graph[J]. Journal of Engineering Science, 2020, 42 (10): 1254- 1266.
4	官赛萍, 靳小龙, 贾岩涛, 等. 面向知识图谱的知识推理研究进展[J]. 软件学报, 2018, 29 (10): 2966- 2994.
	GUAN S P , JIN X L , JIA Y T , et al. Knowledge inference based on knowledge graph[J]. Journal of Software, 2018, 29 (10): 2966- 2994.
5	张仲伟, 曹雷, 陈希亮, 等. 基于神经网络的知识推理研究综述[J]. 计算机工程与应用, 2019, 55 (12): 8- 19.8-19, 36
	ZHANG Z W , CAO L , CHEN X L , et al. A review of knowledge reasoning based on neural network[J]. Computer Engineering and Applications, 2019, 55 (12): 8- 19.8-19, 36
6	漆桂林, 高桓, 吴天星. 知识图谱研究进展[J]. 情报工程, 2017, 3 (1): 4- 25.
	QI G L , GAO H , WU T X . Progress in knowledge graph[J]. Information Engineering, 2017, 3 (1): 4- 25.
7	刘峤, 李杨, 段宏, 等. 知识图谱构建技术综述[J]. 计算机研究与发展, 2016, 53 (3): 582- 600.
	LIU Q , LI Y , DUAN H , et al. A review of knowledge graph construction techniques[J]. Journal of Computer Research and Development, 2016, 53 (3): 582- 600.
8	张钹, 朱军, 苏航. 迈向第三代人工智能[J]. 中国科学: 信息科学, 2020, 50 (9): 1281- 1302.
	ZHANG B , ZHU J , SU H . Towards the third generation of artificial intelligence[J]. Science China: Information Science, 2020, 50 (9): 1281- 1302.
9	LI D , FU Z J , ZHENG Z Y . An entity linking model based on candidate features[J]. Social Network Analysis and Mining, 2021, 11 (1): 50. doi: 10.1007/s13278-021-00761-z
10	WANG Y T, LI Z X, YANG Q, et al. WebEL: improving entity linking with extra web contexts[C]//Proc. of the Web Information Systems Engineering, 2019: 507-522.
11	XIE T , BIN W U , JIA B , et al. Graph-ranking collective Chinese entity linking algorithm[J]. Frontiers of Computer Science, 2020, 14 (2): 291- 303. doi: 10.1007/s11704-018-7175-0
12	FENG H J, DUAN L, ZHANG B Y, et al. A collective entity linking method based on graph embedding algorithm[C]//Proc. of the 5th International Conference on Mechanical, Control and Computer Engineering, 2020: 1479-1482.
13	FINN V K , SHESTERNIKOVA O . A new variant of the genera-lized JSM-method for automatic support of scientific research[J]. Scientific and Technical Information Processing, 2017, 44 (5): 338- 344. doi: 10.3103/S0147688217050045
14	PINGLE A, PIPLAI A, MITTAL S, et al. RelExt: relation extraction using deep learning approaches for cybersecurity knowledge graph improvement[C]//Proc. of the IEEE/ACM International Conference on Advances in Social Networks Ana-lysis and Mining, 2020: 879-886.
15	DASGUPTA S, PIPLAI A, KOTAL A, et al. A comparative study of deep learning based named entity recognition algorithms for cybersecurity[C]//Proc. of the IEEE International Conference on Big Data, 2020: 2596-2604.
16	LIU X, ATHANASIOU C E, PADTURE N P, et al. Knowledge extraction and transfer in data-driven fracture mechanics[J]. Proceedings of the National Academy of Sciences, 2021, 118(23): e2104765118.
17	WU L F, CHEN Y, SHEN K, et al. Graph neural networks for natural language processing: a survey[EB/OL]. [2021-06-13]. https://arxiv.org/abs/2106.06090.
18	YUAN H, YU H Y, GUI S R, et al. Explainability in graph neural networks: a taxonomic survey[EB/OL]. [2021-06-13]. https://arxiv.org/abs/2012.15445.
19	SUN Y N , XU Y J , LI S . Knowledge-aware path: interpretable graph reasoning in proactive dialogue generation[J]. The Journal of China Universities of Posts and Telecommunications, 2021, 28 (1): 1- 9.
20	HOSPEDALES T . Meta-learning in neural networks: a survey[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2021, 44 (9): 5149- 5169.
21	MONDAL A. A survey of reinforcement learning techniques: strategies, recent development, and future directions[EB/OL]. [2021-06-13]. https://arxiv.org/abs/2001.06921.
22	HUISMAN M , RIJN J , PLAAT A . A survey of deep meta-learning[J]. Artificial Intelligence Review, 2021, 54, 4483- 4541. doi: 10.1007/s10462-021-10004-4
23	GHOSH S , BEQUETTE B W . Process systems engineering and the human-in-the-loop: the smart control room[J]. Industrial and Engineering Chemistry Research, 2020, 59 (6): 2422- 2429. doi: 10.1021/acs.iecr.9b04739
24	刘全, 翟建伟, 章宗长, 等. 深度强化学习综述[J]. 计算机学报, 2018, 41 (1): 1- 27.
	LIU Q , ZHAI J W , ZHANG Z C , et al. A review of deep reinforcement learning[J]. Chinese Journal of Computers, 2018, 41 (1): 1- 27.
25	MAZYAVKINA N , SVIRIDOV S , IVANOV S , et al. Reinforcement learning for combinatorial optimization: a survey[J]. Computers & Operations Research, 2021, 134 (1): 105400.
26	GRONAUER S , DIEPOLD K . Multi-agent deep reinforcement learning: a survey[J]. Artificial Intelligence Review, 2022, 55 (2): 895- 943.
27	李晨溪, 曹雷, 张永亮, 等. 基于知识的深度强化学习研究综述[J]. 系统工程与电子技术, 2017, 39 (11): 2603- 2613.
	LI C X , CAO L , ZHANG Y L , et al. A review of knowledge-based deep reinforcement learning[J]. Systems Engineering and Electronics, 2017, 39 (11): 2603- 2613.
28	丁兆云, 贾焰. 微博数据挖掘研究综述[J]. 计算机研究与发展, 2014, 51 (4): 691- 706.
	DING Z Y , JIA Y . A review of microblog data mining[J]. Journal of Computer Research and Development, 2014, 51 (4): 691- 706.
29	BIZER C , LEHMANN J , KOBILAROV G , et al. DBpedia-a crystallization point for the web of data[J]. Web Semantics Science Services and Agents on the World Wide Web, 2009, 7 (3): 154- 165.
30	LIU Y, LI H, GARCIA-DURAN A, et al. MMKG: multi-modal knowledge graphs[C]//Proc. of the European Semantic Web Conference, 2019: 459-474.
31	WANG M , WANG H F , QI G L , et al. Richpedia: a large-scale, comprehensive multi-modal knowledge graph[J]. Big Data Research, 2020, 22 (10): 100159.

[1]	蚁佳才, 刘斌, 姚莉, 赵文涛. 基于知识推理的卫星网络态势理解[J]. 系统工程与电子技术, 2022, 44(5): 1562-1571.
[2]	欧阳志宏, 薛磊, 丁锋. 对光电精确制导武器的区域电子防空干扰目标分配方法[J]. 系统工程与电子技术, 2018, 40(12): 2621-2628.
[3]	苗启广, 刘娟, 宁淑婷. 基于模糊综合评判的机场打击效果评估[J]. Journal of Systems Engineering and Electronics, 2012, 34(7): 1395-1399.

双向循环进化的实体链接及知识推理框架

Bidirectional cyclic evolutionary framework of entity linking and knowledge reasoning

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 31

相关文章 3

编辑推荐

Metrics

本文评价