Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A knowledge map embedding method based on adaptive negative sampling

A technology of knowledge map and negative sampling, which is applied in the field of natural language processing and knowledge map, can solve the problem of not being able to generate learning knowledge map, and achieve the effect of increasing the number of times of training, improving quality, and realizing embedding

Active Publication Date: 2019-02-22
GUILIN UNIV OF ELECTRONIC TECH
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a knowledge map embedding method based on adaptive negative sampling, to solve the problem in the prior art that effective negative examples cannot be generated to help learn the vector representation of the knowledge map. question

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
  • A knowledge map embedding method based on adaptive negative sampling
  • A knowledge map embedding method based on adaptive negative sampling
  • A knowledge map embedding method based on adaptive negative sampling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Embodiments of the present invention are described below through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation modes, and various modifications or changes can be made to the details in this specification based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, in the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

[0030] It should be noted that the diagrams provided in the following embodiments are only schematically illustrating the basic ideas of the present invention, and only the components related to the present invention are shown in the diagrams rather than the number, shape and shape of the compo...

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 provides a knowledge map embedding method based on adaptive negative sampling, which comprises the following steps: step 1, grouping entity vectors according to similarity between entities; 2, utilizing similar entities in the same grouping to replace each other and generate negative case triple similar to positive case triple; 3, taking that positive example triple group and the negative example triple group as the training input of the knowledge map embed in the model; 4, utilizing that loss function of the knowledge map embed model to optimally update the entity vector and therelation vector. The invention improves the similarity between the substituted entity and the substituted entity, thereby improving the quality of the negative example triple. According to the frequency of entities appearing in the knowledge map, the entities are used to improve the training times of high-frequency entities. By improving the quality of negative case triple, the entity and relationship embedding in knowledge map is realized effectively.

Description

technical field [0001] The invention relates to the fields of natural language processing and knowledge graphs, in particular to a knowledge graph embedding method based on adaptive negative sampling. Background technique [0002] The concept of Knowledge Graph (KG) was officially proposed by Google in 2012, and it is mainly used to improve the performance of search engines. In essence, a knowledge graph is a semantic network that expresses various types of entities and the semantic relationships between them. The knowledge graph is a directed graph in which different types of entities are used as nodes, and various relationships between entities are used as edges. Usually, the Resource Description Framework (RDF) standard is used for storage, and the storage form is a triplet (head, relation, tail) (abbreviated as (h, r, t)), where h represents the head entity, and t represents the tail Entity, r represents the relationship between the head entity h and the tail entity t,...

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): G06F16/36G06F17/27
CPCG06F40/289
Inventor 古天龙饶官军常亮秦赛歌王文凯宣闻
Owner GUILIN UNIV OF ELECTRONIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com