Knowledge graph representation learning method based on path tensor decomposition

Abstract

The invention discloses a knowledge graph representation learning method based on path tensor decomposition, comprising the following steps of: step 1, extracting an entity set, a relation set and a triple set in a knowledge graph, and embedding the entity set and the relation set which satisfy a triple into a low-dimensional continuous vector space; step 2, acquiring a path between entities through a PRA (Progressive Refinement Approach) algorithm; step 3, carrying out tensor decomposition on the path where all entities exist possibly, and calculating a decomposition loss function value; step 4, repeating step 3 until a convergent preset value or the maximum number of iteration is reached; step 5, if the maximum number of iteration or the convergent preset value is reached, calculating a next triple-related path, and repeating steps 2 to 4 until all triples of a training set are executed; and step 6, outputting the corresponding entity set and relation set in a training model. The representation learning method can improve the inference accuracy of knowledge discovery and enhance the prediction precision.

Description

technical field [0001] The invention belongs to the fields of knowledge representation, knowledge discovery and artificial intelligence, and in particular relates to a learning method for knowledge map representation based on path tensor decomposition. Background technique [0002] As a new knowledge representation method and data management mode, Knowledge Graph has important applications in natural language processing, question answering, information retrieval and other fields. The knowledge map is a structured semantic knowledge base, which is used to describe concepts and their relationships in the physical world in symbolic form. It mainly uses (head, relation, tail) triples for knowledge representation, head is the head entity, and tail Is the tail entity, relation is the relationship, and the entities are connected to each other through the relationship, forming a network knowledge structure. [0003] Knowledge graph reasoning is to establish a new relationship betwe...

AI Technical Summary

Problems solved by technology

However, the existing reasoning algorithms cannot solve long-path reasoning, and the problem of path reliability and semantic combination is not considered. At the same time, because the relational path reasoning algorithm is still in the early stage of research, there is still a lot of detailed work to be perfected.

Images