Knowledge graph completion method based on multi-semantic learning

A knowledge map and multi-semantic technology, applied in the field of knowledge map completion, to achieve the effect of improving interaction ability and accurate feature representation

Pending Publication Date: 2021-04-16
BEIJING UNIV OF TECH
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] Although the existing methods have made great pr...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Knowledge graph completion method based on multi-semantic learning
  • Knowledge graph completion method based on multi-semantic learning
  • Knowledge graph completion method based on multi-semantic learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0064] experiment

[0065] The models evaluated are on the following public datasets:

[0066] Table 1. List of datasets.

[0067]

[0068] WN18: A subset of Wordnet, it is a database containing lexical relationships between words.

[0069] FB15k: is a subset of Freebase, a large database of real-world facts.

[0070] WN18RR: is a subset of WN18, created by Dettmers et al. by deleting the inverse relationship of WN18.

[0071] FB15k-237: Created by Toutanova et al., noting that the validation and test sets of FB15k and WN18 contain many inverse relationships in the training set, which is more beneficial for simple models. FB15k-237 is a subset of FB15k with the inverse relationship removed.

[0072] 1. Evaluation indicators

[0073] In this experiment, four evaluation criteria were used to evaluate the knowledge map completion model, namely m...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a knowledge graph completion method based on multi-semantic learning. The method comprises the steps of learning entities e1 and r to a plurality of hidden semantic representations through a plurality of conversion matrixes; in the step of embedding and capturing the plurality of hidden semantics of the entity and the relationship in the previous knowledge graph, obtaining a plurality of feature embedding for the same entity or relationship; optimizing embedding of the entity and the relationship by utilizing a deep residual attention network; introducing denoising network optimization entity embedding and relationship embedding; then, simply describing the structure of the denoising network; and introducing a multi-step fusion process to fully fuse entities and relationships; according to the knowledge graph completion method provided by the invention, the problem of a large amount of noise caused by introduction of a plurality of hidden semantics can be effectively reduced. And meanwhile, the denoising network and the multi-step fusion network can fully fuse entities and relationships to obtain the most consistent prediction result.

Description

technical field [0001] The present invention is applicable to the knowledge graph completion technology in the knowledge field, and in particular relates to a knowledge graph completion method based on multi-semantic learning. Background technique [0002] As a collection of human knowledge, knowledge graphs have become important resources for artificial intelligence (AI) and natural language processing (NLP) applications, such as question answering, web search, and semantic analysis. Knowledge representation, especially knowledge embedding, is a fundamental step in knowledge utilization. The embedding of knowledge graph is to learn a continuous mapping, embedding the entities and relations of a structured knowledge graph into a vector space. Knowledge graph embedding has various applications, such as relation extraction, question answering, normalization, recommender systems, dialogue systems, etc. [0003] A knowledge graph is a structured representation of facts, which ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/36G06F16/28G06K9/62G06F40/30G06N3/04G06N3/08
Inventor 尹宝才王家普胡永利孙艳丰王博岳
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap