Knowledge representation learning method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a knowledge representation learning method and device, equipment and a storage medium, and relates to the technical field of natural language processing, deeplearning and knowledge graphs. A specific embodiment of the method comprises the following steps: sampling a knowledge graph sub-graph from a knowledge base; serializing the knowledge graph sub-graphto obtain a serialized text; and reading the serialized text according to the sequence on the knowledge graph sub-graph by using a pre-trained language model, and learning to obtain knowledge representation of each character in the serialized text. According to the embodiment, knowledge representation learning is oriented to entity and relationship representation learning in the knowledge base, semantic association of entities and relationships can be efficiently calculated in a low-dimensional space, the problem of data sparsity is effectively solved, and the knowledge acquisition, fusion and reasoning performances are remarkably improved. By utilizing the strong knowledge acquisition capability and context analysis capability of the pre-trained language model, the knowledge representation learned by the pre-trained language model can better represent the complex relationship in the knowledge base.

Description

technical field [0001] The embodiment of the present application relates to the field of computer technology, specifically to the technical fields of natural language processing, deep learning, and knowledge graph, and especially to a knowledge representation learning method, device, device, and storage medium. Background technique [0002] A knowledge base may refer to a database that stores related data in an orderly manner. Generally, a knowledge base can be represented as a network, with nodes representing entities and edges representing relationships between entities. In the form of network representation, it is usually necessary to design a special knowledge graph to calculate and store and utilize the knowledge base. Designing knowledge graphs is not only time-consuming and labor-intensive, but also plagued by data sparsity. Therefore, representation learning technology represented by deep learning has received extensive attention. Representation learning aims to i...

AI Technical Summary

Problems solved by technology

Designing a knowledge map not only has the disadvantage of time-consuming and laborious, but also suffers from the problem of data sparsity

Images