Open AccessQuestion Answering System Based on Knowledge Graph in Air Defense Field
Author(s) -
Yu Li,
Zhigang Guo,
Gang Chen,
Zhang Xing-xin,
Yongwang Tang,
Wei Han
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1693/1/012033
Subject(s) - computer science , knowledge graph , question answering , construct (python library) , graph , field (mathematics) , set (abstract data type) , domain (mathematical analysis) , domain knowledge , artificial intelligence , theoretical computer science , programming language , mathematical analysis , mathematics , pure mathematics
With the development of artificial intelligence technology, question answering systems based on knowledge graphs (QAS-KGs) have become a prevalent information retrieval approach. However, current QAS-KGs which usually adopt general knowledge graphs have complex algorithms and high requirements for hardware. Moreover, in some specific fields, such as air defense field, the QAS-KGs usually cannot respond accurately and they can only handle questions composed of one language. In this paper, we introduce an efficient QAS-KG approach which can handle questions composed of Chinese, English, or both languages. First, we construct the knowledge graph in air defense field according to the domain characteristics and user needs. Then we design and implement a question answering system based on the knowledge graph. Finally, we test the system on the self-built data set. The results show that the system can understand the user’s intention quickly and make accurate responses without high requirements for hardware.