Knowledge graph representation learning method fusing entity description and types

Abstract

The invention provides a knowledge graph representation learning method fusing entity description and types. The method comprises the following steps of S1, obtaining embedding of a triple entity by utilizing a translation model, and taking a relationship in a triple as a translation operation between a head entity and a tail entity to obtain numerical vector representation of each triple entity and the relationship; s2, adopting a Doc2Vec model to embed the text information described by the entity; s3, combining entity embedding obtained through a Transform model with the entity hierarchicaltype mapping matrix to obtain embedding of a triple entity type; and S4, connecting all the representation vectors to obtain a final triad entity vector, optimizing the training model by adopting a random gradient descent method, and carrying out effect evaluation. According to the method provided by the invention, through entity description and entity type embedding, semantic information expressed by knowledge graph triad entities is improved.

Description

technical field [0001] The present invention relates to the field of knowledge graphs, in particular to a knowledge graph representation learning method that integrates entity descriptions and types. Background technique [0002] In 2012, Google proposed the concept of knowledge graph and applied it to the search engine. Since then, great progress has been made in the construction of large-scale knowledge graphs, and a large number of knowledge graphs have emerged, representative ones are YAGO, DBpedia, FreeBase, etc. At present, knowledge graphs play an important role in many artificial intelligence applications, such as intelligent question answering, information recommendation, web search, etc. A knowledge graph is a structured semantic network that stores a large number of fact triples (head entity, relation, tail entity), which are usually simplified as (h, r, t). [0003] However, with the gradual expansion of the scale of knowledge graphs, the diversification of dat...

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to overcome the above-mentioned defects in the prior art, and propose a knowledge map representation learning method that combines entity description and type, which can solve the problem that most current representation learning models only consider the triple information of the knowledge map. The rich text information and type information in the map have a low degree of fusion and a single fusion method, which can well reduce the ambiguity of entities and relationships, improve the accuracy of reasoning and prediction, and improve the semantic information represented by triplet entities in the knowledge map.

Images