模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2021, Vol. 34 Issue (1): 33-43    DOI: 10.16451/j.cnki.issn1003-6059.202101004
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Knowledge Base Completion Based on Multimodal Representation Learning
WANG Jingbin1, SU Hua1, LAI Xiaolian1
1. College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350108

Download: PDF (711 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  In most learning models for knowledge graph representation, only structural knowledge between entities and relations is taken into account. Therefore, the capability of the models is limited by knowledge storage, and the completion performance of knowledge base is unstable. Existing knowledge representation methods incorporating external information mostly model for a specific kind of external modal information, leading to limited application scopes. Thus, a knowledge representation learning model, Conv-AT, is proposed. Firstly, two external modes of information, text and images, are considered, and three schemes fusing external knowledge and entities are introduced to obtain multimodal representation of entities. Secondly, the performance of convolution is enhanced and the quality of knowledge representation as well as the completion ability of the model are improved by combining the channel attention module and spatial attention module. Link prediction and triple classification experiments are conducted on public multimodal datasets, and the results show that the proposed method is superior to other methods.
Key wordsKnowledge Graph      Link Prediction      Multimodal      Representation Learning     
Received: 27 September 2020     
ZTFLH: TP 391  
Fund:National Natural Science Foundation of China(No.61672159), Industry-University-Research Collaboration Program in Fujian Province of China(No.2017H6008,2018H6010)
Corresponding Authors: WANG Jingbin, master, associate professor. Her research interests include knowledge graph, relation reasoning, distributed data management and know-ledge representation.   
About author:: SU Hua, master student. Her research interests include knowledge graph, relation reasoning and knowledge representation.
LAI Xiaolian, master student. Her research interests include knowledge graph, relation reasoning and knowledge representation.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
WANG Jingbin
SU Hua
LAI Xiaolian
Cite this article:   
WANG Jingbin,SU Hua,LAI Xiaolian. Knowledge Base Completion Based on Multimodal Representation Learning[J]. , 2021, 34(1): 33-43.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202101004      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2021/V34/I1/33
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn