Knowledge graph representation learning method and system based on text graph enhancement

Abstract

The invention belongs to the technical field of knowledge graphs, and particularly relates to a knowledge graph representation learning method and system based on text graph enhancement, and the method comprises the steps: carrying out the analysis processing of knowledge graph entity text description, extracting a named entity, and constructing a two-layer heterogeneous text graph formed by sentence layer nodes and text entity layer nodes; establishing a connection between the text graph entity and the knowledge graph entity, obtaining an enhanced knowledge graph, and processing to obtain a node initialization representation; performing semantic propagation among entities by adopting a graph convolutional neural network to obtain entity text representation fusing text content semantics and triple structure semantics; entity text representation is combined with entity structure representation which only considers triples, and updating and optimization are carried out through negative samples and loss functions. According to the method, entity text content semantics can be better fused into the knowledge graph, the sparsity problem of the knowledge graph is effectively relieved, the expression ability of knowledge graph representation learning is improved, and the method also has good applicability under the condition of few samples or zero samples.

Description

technical field [0001] The invention belongs to the technical field of knowledge graphs, and in particular relates to a method and system for learning a knowledge graph representation based on text graph enhancement. Background technique [0002] The origin of Knowledge Graph can be traced back to the 1950s. In 2012, Google officially proposed the concept of Knowledge Graph and used it in search engines, which greatly improved its performance. With the rapid development of artificial intelligence and the support of big data, Internet of Things, natural language processing and other technologies, knowledge graphs have played an important role in promoting various social industries such as security, finance, justice, transportation, technology, and medical care. It is also often used as one of the core supporting technologies in the fields of intelligent question answering and recommendation systems. Therefore, it is of great practical significance to carry out research on kn...

AI Technical Summary

Problems solved by technology

However, such models often use independent encoding when combining text information, and it is difficult to better integrate the semantics of triplet structure and content semantics of auxiliary information such as text, so the performance of the model needs to be further improved

Images