Research Area:  Machine Learning

Abstract:

Entity alignment plays an essential role in the knowledge graph (KG) integration. Though large efforts have been made on exploring the association of relational embeddings between different knowledge graphs, they may fail to effectively describe and integrate the multi-modal knowledge in the real application scenario. To that end, in this paper, we propose a novel solution called Multi-Modal Entity Alignment (MMEA) to address the problem of entity alignment in a multi-modal view. Specifically, we first design a novel multi-modal knowledge embedding method to generate the entity representations of relational, visual and numerical knowledge, respectively. Along this line, multiple representations of different types of knowledge will be integrated via a multi-modal knowledge fusion module. Extensive experiments on two public datasets clearly demonstrate the effectiveness of the MMEA model with a significant margin compared with the state-of-the-art methods.

Keywords:  
Multi-modal knowledge
Entity alignment
Knowledge graph
Machine Learning
Deep Learning

Author(s) Name:  Liyi Chen, Zhi Li, Yijun Wang, Tong Xu, Zhefeng Wang & Enhong Chen

Publisher name:  Springer

DOI:  10.1007/978-3-030-55130-8_12

Volume Information:  

Paper Link:   https://link.springer.com/chapter/10.1007/978-3-030-55130-8_12