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

Vector space model based relative mapping method

A vector space, mapping method technology, applied in special data processing applications, instruments, electrical digital data processing and other directions, can solve the problem that relational words cannot be directly converted into

Inactive Publication Date: 2018-06-12
NANKAI UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that relational words in natural language cannot be directly converted into predicates in RDF graph data to generate structured language, and in combination with the calculation method of vector similarity in vector space model, a kind of relational word mapping based on vector space model is proposed method

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
  • Vector space model based relative mapping method
  • Vector space model based relative mapping method
  • Vector space model based relative mapping method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The processing flow of the inventive method is as figure 1 shown.

[0058] The specific implementation of the method of the present invention will be described below in conjunction with examples. Table 1 shows some natural language triples, including relational words and entity pairs. A portion of RDF graph data such as figure 2 shown, where figure 2 The red path in is a possible predicate candidate of the relative word wasbornin. Combine the following figure 2 Shown RDF graph data introduces the concrete steps of the inventive method:

[0059] Table 1 Natural language triples

[0060]

[0061]

[0062] Step 1: Identify predicate candidates for relational words

[0063] Firstly, find the corresponding vertices in the RDF graph data for an entity pair of a relational word according to the label, and then traverse the simple path between the vertices. There is a closed loop, and for the sake of efficiency, the length of the path is set to no more than 3. ...

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 belongs to the field of natural language processing and discloses a vector space model based relative mapping method. The method includes steps: firstly, according to a corresponding relation between relatives and entity pairs, constructing a characteristic vector of each vector by statistics of entity pair occurrence frequency and specificity; secondly, adopting a vector space modelto calculate similarity of the relatives to corresponding predicates, and selecting high-similarity predicates as candidates of the relatives; finally, sorting all candidates of the relatives, and selecting the predicate candidates highest in reliability to construct a mapping dictionary. By adoption of the relative predicate mapping method, an effective solution can be provided for automatic mapping of the relatives in natural languages and the predicates in RDF graph data, and converting the natural languages into the graph data to realize corresponding matching is realized.

Description

technical field [0001] The invention belongs to the field of natural language processing, and in particular relates to a novel technique for mapping predicates between relational words in natural language and RDF graph data. Background technique [0002] With the development of computer technology, digital information has multiplied, and massive amounts of data are available to people. However, in the face of a large amount of accumulated data formed by the explosive growth of information, text-based search engines can only sort and index according to keywords, and cannot really answer the questions raised by users. At the same time, more and more knowledge graphs are beginning to appear, eager to understand and answer users' questions directly through structured information and RDF question-and-answer technology. In the RDF question answering system, the processing of natural language is particularly important. Natural language generally contains elements such as relation...

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): G06F17/27
CPCG06F40/284G06F40/295G06F40/30
Inventor 温延龙刘云鹏袁晓洁
Owner NANKAI UNIV
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