Knowledge graph representation learning method fusing entity description, hierarchical types and text relation information

Abstract

The invention discloses a knowledge graph representation learning method fusing entity description, hierarchical types and text relation information. The knowledge graph representation learning methodcomprises the following steps: firstly, preprocessing a knowledge base and a corpus, and extracting structured information (triple), entity description information, hierarchical type information andtext relation information; secondly, learning the representation based on the structured information by using a translation-based model TransE; learning a representation based on the entity description information by using the CNN; constructing a mapping matrix of an entity hierarchical type by using WHE, learning a representation based on hierarchical type information, learning a representation of sentences by using a position-based PCNN, allocating a weight to each sentence by using a sentence level attention mechanism, and learning a representation based on text relation information; and then constructing a total energy function and a total loss function of the model according to the representation based on the four kinds of information. The knowledge graph representation learning method carries out learning on the model parameters in combination with a loss function, and finally obtains optimized entities and relation representations.

Description

technical field [0001] The invention relates to the field of knowledge graph representation learning, in particular to a knowledge graph representation learning method that integrates entity description, hierarchical type, and text relationship information. Background technique [0002] In recent years, with the continuous development of Internet technology and application models, the explosive growth of Internet data has been triggered. How to mine valuable information from massive data has become a challenge. Therefore, the knowledge map came into being. The knowledge graph represents everything in the world and the connections between them in the form of triples (head entity, relationship, tail entity). With the advent of the Web3.0 era, knowledge graphs containing a large amount of semantic knowledge are widely used in data mining, information Retrieval and question answering systems and other fields. Although the existing knowledge graph already contains a large numbe...

AI Technical Summary

Problems solved by technology

However, most of the existing translation-based models only use the structural information in the knowledge graph, and do not make good use of additional information such as entity description information, textual relationship information, and type information.

Some models that use additional information also have some problems. For example, when using textual relationship information, the influence of different sentences on the relationship is not considered, and there is a noise problem.

In addition, the existing models that utilize additional information do not introduce additional information to both relationships and entities, and there is room for further improvement in performance

Images