CAREA: Cotraining Attribute and Relation Embeddings for Cross-Lingual Entity Alignment in Knowledge Graphs. (8th December 2020)

• Record Type: Journal Article
• Authors: Chen, Baiyang; Chen, Xiaoliang; Lu, Peng; Du, Yajun
• Other Names: Guirao Juan L. G. Academic Editor.
• Is Part Of: Discrete dynamics in nature and society. Volume 2020(2020)
• Publication Date: 2020-12-08
• Subjects: System analysis -- Periodicals; Dynamics -- Periodicals; Chaotic behavior in systems -- Periodicals; Differentiable dynamical systems -- Periodicals; 003.05
• DOI: 10.1155/2020/6831603
• Languages: English
• ISSNs: 1026-0226

Abstract

Abstract : Knowledge graphs (KGs) are one of the most widely used techniques of knowledge organizations and have been extensively used in many application fields related to artificial intelligence, for example, web search and recommendations. Entity alignment provides a useful tool for how to integrate multilingual KGs automatically. However, most of the existing studies evaluated ignore the abundant information of entity attributes except for entity relationships. This paper sets out to investigate cross-lingual entity alignment and proposes an iterative cotraining approach (CAREA) to train a pair of independent models. The two models can extract the attribute and the relation features of multilingual KGs, respectively. In each iteration, the two models alternate to predict a new set of potentially aligned entity pairs. Besides, this method further filters through the dynamic threshold value to enhance the two models' supervision. Experimental results on three real-world datasets demonstrate the effectiveness and superiority of the proposed method. The CAREA model improves the performance with at least an absolute increase of 3.9% across all experiment datasets. The code is available at https://github.com/ChenBaiyang/CAREA .