Knowledge graph representation learning method

A knowledge map and vector technology, applied in the field of knowledge map representation learning, can solve the problem of not being able to accurately represent entities, relationships, and characteristics

Inactive Publication Date: 2016-06-01
TSINGHUA UNIV
View PDF0 Cites 72 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to solve the problems in the prior art that cannot accurately represent the connections between entities, relationships and characteristics, so as to improve the quality of knowledge graph representation

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 representation learning method
  • Knowledge graph representation learning method
  • Knowledge graph representation learning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0017] The invention discloses a knowledge graph representation learning method, and its flow diagram is as figure 2 As shown, the method includes:

[0018] Step 21: Use the translation-based model between the entity vector and the relationship vector to define the correlation between the entity vector and the relationship vector in the relationship triples (head, relationship, tail).

[0019] Among them, using the translation-based model between the entity vector and the relationship vector to define the correlation between the entity vector and the relationship vector in the relationship triplet includes:

[0020] S211. Define the probability of the relational triplet as p ( h | r , t , X ) = exp ( g ( h , r , t ) ) X h ‾ exp ( g ( h ‾ , r , t ) ) ;

[0021] Represent any entity in the knowledge graph; It is the normalization factor of the probability function of the relationship ...

Embodiment 2

[0045] Since the knowledge graph representation learning method of the present invention treats relationships and characteristics differently, further, the mutual connection between characteristics can be considered.

[0046] The knowledge graph representation learning method of the second embodiment of the present invention includes the following steps:

[0047] Step 31: Use the translation-based model between the entity vector and the relationship vector to define the correlation between the entity vector and the relationship vector in the relationship triples (head, relationship, tail).

[0048] Among them, using the translation-based model between the entity vector and the relationship vector to define the correlation between the entity vector and the relationship vector in the relationship triplet includes:

[0049] S311. Define the probability of the relational triplet as p ( h | r , t , X ) = exp ( g ( h , r , t ) ) X ...

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 representation learning method. The method comprises the following steps: defining the correlation between entity vectors and relation vectors in a relation triple (head, relation, tail) by utilizing a translation-based model between the entity vector and the relation vector; defining the correlation between entity vectors and feature vectors in a feature triple (entity, attribute, value) by utilizing a neural network classification model; and correlating the entity vectors, the relation vectors and the feature vectors with one another through an evaluation function, and minimizing the evaluation function to learn the entity vectors, the relation vectors and the feature vectors so as to achieve the optimization aim. By adopting the method disclosed in the invention, the relation among the entity, the relation and the feature can be accurately represented.

Description

Technical field [0001] The present invention relates to the fields of natural language processing and knowledge graphs, in particular to a knowledge graph representation learning method. Background technique [0002] With the rapid development of society, we have entered the era of information explosion, and massive new entities and information are generated every day. The Internet is the most convenient information acquisition platform today, and users have an increasingly urgent need for effective information screening and summarization. How to obtain valuable information from massive data has become a problem. The knowledge graph came into being. [0003] The knowledge graph represents all the proper nouns and things in the world such as people, place names, book names, and team names as entities, and represents the internal connections between entities as relationships, and aims to represent the massive knowledge in the database as between entities Use relationships as a tern...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30
CPCG06F16/288
Inventor 孙茂松林衍凯刘知远栾焕博刘奕群马少平
Owner TSINGHUA UNIV
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