A knowledge map representation learning method based on structure information and text description

Abstract

A knowledge map representation learning method based on structure information and text description aims at mapping entities and relationships in a triple into a low-dimensional continuous real value space. The invention aims at improving vector representation of entities in knowledge representation; The corresponding text description information of the entity is obtained from the existing knowledge base Freebase, Word2vec is used to represent each description with a word vector, Then, the description vector is represented by word addition and mean vector, and the description vector is represented by doc2vec sentence vector. Then, the word vector is used as the input of CNN text encoder to obtain the description text-based representation vector of each entity. In the joint representation, weights are used to evaluate the symbol-based representation vectors in the knowledge base, and the effects of the representation vectors based on network structure and description text on the final representation vectors of entities are analyzed, so as to achieve the fusion of structure information and text information, and improve the accuracy of knowledge map representation.

Description

technical field [0001] The present invention specifically relates to a knowledge map representation learning method based on structural information and text description. Background technique [0002] Knowledge graph is an important part of NLP technology in tasks such as intelligent question answering, web search and semantic analysis. Knowledge graphs are often huge in scale, containing hundreds of entities and billions of knowledge, but are usually incomplete. Therefore, knowledge map completion is used to solve the problem of data sparsity in knowledge maps. Knowledge graphs are often represented in the form of a network, where nodes represent entities, edges represent the relationship between two entities, and each piece of knowledge is represented in the form of a triple (head entity, relationship, tail entity). Based on symbolic representation methods such as triples, designers must design various graph algorithms for different applications in knowledge graph complet...

AI Technical Summary

Problems solved by technology

[0004] For example, the triplet based on the text description in the knowledge base Fressbase, in which the text description corresponding to each entity provides certain semantic information for the representation of the entity in the triplet, but in many knowledge map representation learning methods , when dealing with these triples, the symbol-based triple learning only considers the structural information representation of the triple itself; the text-based representation learning method simply concatenates the structural information vector and the text information vector; it does not efficiently Use the semantic information in the text to improve the reasonable representation of the entity in the vector space; moreover, the relative structure information of the entity in the map is not added to the representation vector of the entity, and the information of the entity is lost to a certain extent

Images