Survey on Embedding Models for Knowledge Graph and its Applications

TL;DR

This survey reviews various knowledge graph embedding models, focusing on translation-based and neural network-based approaches, and explores their applications across different domains utilizing deep learning and social media data.

Contribution

It provides a comprehensive overview of KG embedding models and discusses their diverse applications, highlighting recent advances and challenges.

Findings

Different KG embedding models capture semantic relations effectively.

Applications include deep learning models and social media data analysis.

The survey identifies key challenges and future directions in KG embedding.

Abstract

Knowledge Graph (KG) is a graph based data structure to represent facts of the world where nodes represent real world entities or abstract concept and edges represent relation between the entities. Graph as representation for knowledge has several drawbacks like data sparsity, computational complexity and manual feature engineering. Knowledge Graph embedding tackles the drawback by representing entities and relation in low dimensional vector space by capturing the semantic relation between them. There are different KG embedding models. Here, we discuss translation based and neural network based embedding models which differ based on semantic property, scoring function and architecture they use. Further, we discuss application of KG in some domains that use deep learning models and leverage social media data.