Bidirectional cyclic evolutionary framework of entity linking and knowledge reasoning

被引：0
作者：
Feng H. [1 ]
Duan L. [1 ]
Zhang B. [1 ]
Liu H. [1 ,2 ]
机构：
[1] College of Electronic Engineering, Naval University of Engineering, Wuhan
[2] Unit 91202 of the PLA, Huludao
来源：
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2022年 / 44卷 / 09期
关键词：
bidirectional control; entity linking; knowledge reasoning; modular design; natural language processing;
D O I：
10.12305/j.issn.1001-506X.2022.09.22
中图分类号：
学科分类号：
摘要：
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. © 2022 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码：2878 / 2885
页数：7
相关论文
共 32 条
  • [1] OLIVEIRA I L, FILETO R, SPECK R, Et al., Towards holistic entity linking: survey and directions, Information Systems, 95, (2021)
  • [2] MYTHREI S, SINGARAVELAN S., Survey on entity linking for domain specific with heterogeneous information networks, Informatologia, 53, 3, pp. 173-184, (2020)
  • [3] MA Z G, NI R Y, YU K H., Recent advances, key technologies and challenges in knowledge graph, Journal of Engineering Science, 42, 10, pp. 1254-1266, (2020)
  • [4] GUAN S P, JIN X L, JIA Y T, Et al., Knowledge inference based on knowledge graph, Journal of Software, 29, 10, pp. 2966-2994, (2018)
  • [5] ZHANG Z W, CAO L, CHEN X L, Et al., A review of knowledge reasoning based on neural network, Computer Engineering and Applications, 55, 12, pp. 8-19, (2019)
  • [6] QI G L, GAO H, WU T X., Progress in knowledge graph, Information Engineering, 3, 1, pp. 4-25, (2017)
  • [7] LIU Q, LI Y, DUAN H, Et al., A review of knowledge graph construction techniques, Journal of Computer Research and Development, 53, 3, pp. 582-600, (2016)
  • [8] ZHANG B, ZHU J, SU H., Towards the third generation of artificial intelligence, Science China: Information Science, 50, 9, pp. 1281-1302, (2020)
  • [9] LI D, FU Z J, ZHENG Z Y., An entity linking model based on candidate features, Social Network Analysis and Mining, 11, 1, (2021)
  • [10] WANG Y T, LI Z X, YANG Q, Et al., WebEL: improving entity linking with extra web contexts, Proc. of the Web Information Systems Engineering, pp. 507-522, (2019)
1234