Back to Search Start Over

A military legal question answering system based on retrieval and knowledge graph

Authors :
LIU Yiming, XIE Zhenjie, FU Wei, XU Ruilin
Source :
Zhihui kongzhi yu fangzhen, Vol 45, Iss 6, Pp 89-95 (2023)
Publication Year :
2023
Publisher :
Editorial Office of Command Control and Simulation, 2023.

Abstract

Military regulations are of great significance to modern military operations. However, consulting the texts is inefficient and error-prone. A military legal question answering system is constructed by integrating retrieval and knowledge graph technologies. The optimized TF-IDF model is used to establish a data structure for the hierarchical retrieval of laws and regulations to improve the efficiency. Knowledge graph technologies are used to generate a large amount of knowledge for the clauses of laws and regulations, ensuring the ability of question understanding. According to the characteristics of military laws and regulations, the algorithms of question processing and clause retrieval are designed, and the complete answer is composed of a short answer, clause content and an answer source. Analysis and testing show that the underlying data constructed is highly hierarchical and semantically rich. The prototype system can accurately answer questions from multiple perspectives, and it combines the advantages of retrieval and knowledge graph technologies. The system can provide decision aid for the commander to deal with legal problems, and the technologies are also applicable to regulations in other fields.

Details

Language :
Chinese
ISSN :
16733819
Volume :
45
Issue :
6
Database :
Directory of Open Access Journals
Journal :
Zhihui kongzhi yu fangzhen
Publication Type :
Academic Journal
Accession number :
edsdoj.7c715b3faa6c4f06bd6a06f5a86a626b
Document Type :
article
Full Text :
https://doi.org/10.3969/j.issn.1673-3819.2023.06.014