System and method for generating natural language to SPARQL statement based on GCN and pointer network

A natural language and sentence technology, applied in the field of natural language to SPARQL statement generation system, can solve problems such as deep semantic analysis of unfavorable questions and complicated SPARQL statement generation process, so as to improve generation flexibility, reduce generation complexity, and avoid The effect of the middle link

Active Publication Date: 2021-04-09
XI AN JIAOTONG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a system and method for generating SPARQL statements from natural language based on GCN and pointer network, which solves the problem that the generation process of SPARQL statements is complex and difficult. Defects that are conducive to deep semantic analysis of questions

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
  • System and method for generating natural language to SPARQL statement based on GCN and pointer network
  • System and method for generating natural language to SPARQL statement based on GCN and pointer network
  • System and method for generating natural language to SPARQL statement based on GCN and pointer network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

[0054] With the development of deep learning technology, it is possible to directly generate SPARQL statements for Text questions. This paper studies a method of generating natural language to SPARQL statements based on GCN and pointer network, which can solve the problems mentioned in the background technology.

[0055] refer to figure 1 A method for generating a SPARQL statement from a natural language based on a GCN and a pointer network provided in an embodiment of the present invention includes the following steps:

[0056] S1. Receiving a question statement;

[0057] S2...

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 system and a method for generating a natural language to SPARQL statement based on a GCN and pointer network. The method comprises the steps of acquiring a question statement graph; training the obtained question statement graph by using a GCN neural network model to obtain a graph embedding vector corresponding to each node in the question statement graph; establishing a pointer network architecture, and using the pointer network architecture for generating the SPARQL statement. End-to-end generation is realized, intermediate links are avoided, and the generation complexity of the SPARQL statement is reduced; and the generation flexibility of decoding end questions is improved.

Description

technical field [0001] The invention relates to the field of natural language processing of a method for generating SPARQL statements, in particular to a system and method for generating SPARQL statements from natural language based on GCN and a pointer network. Background technique [0002] With the development of Internet technology, question answering system plays an important role in information retrieval. Its research and development has gone through expert system, retrieval question answering, community question answering and current knowledge base question answering, and has a very long history. Knowledge base question answering, as an important type of question answering system, generates knowledge base-oriented SPARQL statements through semantic understanding and parsing of questions, and then uses knowledge base to query and reason to get answers. Among them, using Jena to store knowledge graphs and using SPARQL statements to query to obtain answers is an important...

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): G06F16/332G06F16/33G06F16/36G06F40/284G06F40/30G06N3/04G06N3/08
CPCG06F16/3329G06F16/3344G06F16/367G06F40/284G06F40/30G06N3/08G06N3/044G06N3/045
Inventor 姜洪超金莉
Owner XI AN JIAOTONG 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