Construction method of knowledge graph under machine learning. (9th March 2022)

• Record Type: Journal Article
• Authors: Han, Peifu; Guo, Junjun; Lai, Hua; Song, Qianli
• Is Part Of: International journal of grid and utility computing. Volume 13:Number 1(2022)
• Page Start: 11
• Page End: 20
• Publication Date: 2022-03-09
• Subjects: Vietnamese -- named entity recognition -- residual network -- knowledge graph; Electronic data processing -- Distributed processing -- Periodicals; Electronic commerce -- Management -- Computer programs -- Periodicals; 004.605
• Languages: English
• ISSNs: 1741-847X

Abstract

With the increasing trade among China and Southeast Asian countries, cultural exchanges have become more and more intensified. Convenient language communication constitutes an important part of the cooperation channels among different countries. To explore the named entity recognition (NER) in the field of knowledge graph construction, the Vietnamese grammar and word formation are analysed deeply in this study, aiming to solve the low recognition precision and low network calculation efficiency in Vietnamese named entity recognition. Firstly, the Vietnamese person names, location names, and institution names in Vietnamese corpus are collected statistically to build a corresponding entity database to assist the Vietnamese named entity recognition. Then, a Vietnamese named entity recognition model is proposed based on residual dense block (RDB) convolutional neural network (CNN).