Application of Entity Relation Extraction Method Under CRF and Syntax Analysis Tree in the Construction of Military Equipment Knowledge Graph

Chenguang Liu,Xingxin Li,Yongli Yu,Peng Wang

doi:10.1109/access.2020.3034894

Chenguang Liu, Xingxin Li + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.3034894

Copy DOI

Abstract

In the field of military research, manufacturing and management of weapons and equipment are very important. Due to the continuous advancement of science and technology, many military equipment databases have a loose structure, which makes them difficult to be utilized efficiently, resulting in low efficiency, chaotic management, and other issues. In order to solve these problems, an entity-relation extraction method based on CRF and syntactic analysis tree is proposed according to the latest text extraction algorithm. Finally, a military knowledge graph construction method is optimized via massive data training, model comparison and improvement. The ternary data extraction method is significantly better than the single algorithm extraction method, and the accuracy of the extracted training model can reach 72%. Compared with the traditional entity-relation extraction method, the accuracy of the entity-relation extraction method based on the fusion of CRF and syntax analysis tree is improved by 12.6% when the confidence model is added, and the comprehensive evaluation accuracy can reach 78.11%. This result has significant practical value for the construction of knowledge graphs in the field of military equipment.

Highlights

With the continuous development of informatization, the data generated in various industries has increased dramatically
The results show that the overall accuracy, recall rate, and F value of the entity relation extraction method based on the maximum entropy model are higher than the original entity relation extraction method combining CRF and syntax analysis tree
After adding the confidence threshold, the entity relation combining CRF and the syntax analysis tree is significantly higher than the entity relation extraction method based on the maximum entropy model

Summary

Introduction

With the continuous development of informatization, the data generated in various industries has increased dramatically. Gui (2018) proposed a method to calculate tracking quality based on armament data [4]. It is impossible to deeply mine and apply the data [6]. Most of these massive data on the Internet are high-quality and semistructured knowledge. Many entries are edited manually and contain much-standardized knowledge, such as article titles, classification labels, and information frames. The feasibility of using these data to construct a knowledge graph is high

Methods

Results

Conclusion