Deep learning in knowledge graph

Abstract

Knowledge Graph (KG) is a fundamental resource for human-like commonsense reasoning and natural language understanding, which contains rich knowledge about the world's entities, entities' attributes, and semantic relations between different entities. Recent years have witnessed the remarkable success of deep learning techniques in KG. In this chapter, we introduce three broad categories of deep learning-based KG techniques: (1) knowledge representation learning techniques which embed entities and relations in a KG into a dense, low-dimensional, and real-valued semantic space; (2) neural relation extraction techniques which extract facts/relations from text, which can then be used to construct/complete KG; (3) deep learning-based entity linking techniques which bridge Knowledge Graph with textual data, which can facilitate many different tasks.