Knowledge Graphs (KGs) Entity Alignment (EA) WEB 3.0 Technologies

Seeking similar entity pairs pointing to their counterpart real-world objects in knowledge graphs (KGs) is one of the most challenging and critical steps for entity alignment (EA), also known as KG integration. EA has prompted the development of knowledge-based technologies such as recommender systems, semantic search engines, chatbot systems, and knowledge reasoning. Recent years have witnessed increasing interest in representation learning-based entity alignment methods. Most of these represent different KG entities as low-dimensional vector embeddings via their neighborhood structure and then find counterpart entities by estimating the similarities between entity representations.

Due to the heterogeneity of the knowledge graph, it is difficult to achieve satisfactory alignment results for entity alignment methods based on structure encoding.

Figure 1: Samsung's relationship semantic context and neighborhood structure map in the DBpedia knowledge graph.

Figure 2: Simple visualization of Relational Semantics Augmentation-based architecture for EA and processing multilingual KGs

Source:

Akhtar, M. U., Liu, J., Xie, Z., Liu, X., Ahmed, S., & Huang, B. (2022). Entity alignment based on relational semantics augmentation for multilingual knowledge graphs. Knowledge-Based Systems, 109494.