Knowledge representation learning method fusing multi-source information

Abstract

The invention discloses a knowledge representation learning method fusing multi-source information, and belongs to the technical field of natural language processing. The method comprises the following steps: combining hierarchical type information of an entity, text description information of the entity, graph topological structure information and a triple through an encoder model to obtain a preliminary fusion result of multi-source information; and inputting the preliminary fusion vector of the multi-source information into a decoder model for further training to obtain a final entity vector and a relationship vector. Entity hierarchy type information, entity text description information, graph structure information and an original triad are combined through a self-defined encoder, so that the characteristics of entities and relationships in a knowledge graph can be more fully expressed; anda ConvKB model is used as a decoder, a result vector generated by the encoder is input into the convolutional neural network for semantic matching, and global information among different dimensions of the triad is captured.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and more specifically relates to a knowledge representation learning method that integrates multi-source information. Background technique [0002] A knowledge graph is a large-scale network that stores entities, semantic types, attributes, and relationships between entities. In recent years, people have spent a lot of time building knowledge graphs in various fields, such as WordNet, Freebase, DBpedia, YAGO, NELL, and Wikidata. Knowledge graph is a tool to organize human's existing knowledge into a structured system, which provides us with a new perspective to describe the real world. Today, knowledge graphs play an important role in many tasks of artificial intelligence and intelligent information services, such as word similarity calculation, word sense disambiguation, entity disambiguation, semantic parsing, topic indexing, document summarization, information extraction, ...

AI Technical Summary

Problems solved by technology

However, the use of knowledge graphs in practical applications still faces two major challenges: (1) low computational efficiency: although the use of graph structures to represent knowledge is concise and intuitive and in line with people’s experience, when performing retrieval and multi-step reasoning tasks, Generally, special graph theory algorithms are used

However, the time and space complexity of the graph theory algorithm is large, and it is difficult to apply it to a large-scale knowledge map.

(2) Data sparsity: In large knowledge bases, many times rare entities are only related to few relations, which leads to long-tail distribution problem

In the era of information explosion, a lot of new knowledge is added to the knowledge graph every day, and the one-hot representation usually suffers from low computational efficiency and insufficient scalability.

Images