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

Improved method for entity links in simple questions and answers based on knowledge graph

A knowledge graph, entity technology, applied in the field of big data, can solve problems such as complex model and entity confusion

Active Publication Date: 2020-03-24
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In recent years, some neural network models combined with attention mechanisms have been continuously proposed. In entity linking, the main task of this model is to make the vectorization of the problem better represent the information related to the entity, which is the information about the entity in the problem. Some can be utilized to maximize, but this model is generally more complex and does not deal well with the problem of entity confusion

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
  • Improved method for entity links in simple questions and answers based on knowledge graph
  • Improved method for entity links in simple questions and answers based on knowledge graph
  • Improved method for entity links in simple questions and answers based on knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] like figure 1 An improved method for entity linking in simple question answering based on knowledge graph is shown, including the following steps:

[0035] Step 1: establish a central server and a problem input client, the problem input client is used to collect problem data, and transmit the problem data to the central server for processing through the Internet;

[0036] Establish an entity detection module, an entity candidate set module, a knowledge map retrieval module, and an entity matching module in the central server;

[0037] The knowledge graph retrieval module is used to connect with the open source knowledge graph KG and provide retrieval services related to the open source knowledge graph KG;

[0038] Step 2: After the central server receives the question data, the entity detection module detects the question data, and predicts the subject words of the question in the question data. The steps are as follows:

[0039] Step A1: Build a BILSTM-CRF model for ...

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 an improvement method for entity links in simple questions and answers based on a knowledge graph. The invention belongs to the technical field of natural language processing.The improved method includes the steps: establishing a central server and a problem input client; establishing an entity detection module, an entity candidate set module, a knowledge graph retrieval module and an entity matching module in a central server; detecting problem data, establishing entity candidate sets, encoding problem data, enabling entities in an entity candidate set to be subjectedto three-level coding; and selecting n entities with the highest matching scores with the problem data from the entity candidate set. By adopting a unique problem coding mode, the invention providesa method for coding entities at three levels, fully utilizes the type information and name information of the entities, and effectively solves the problems of entity confusion and OOV in combination with the problem coding mode.

Description

technical field [0001] The invention belongs to the technical field of big data, and relates to an improved method for entity linking in simple question and answer based on knowledge graph. Background technique [0002] In recent years, more and more open-source knowledge graphs (KGs) containing a large number of facts have appeared, such as FreeBase, Yago, and DBpedia. Question answering (KG-QA) with knowledge graph as answer source is a hot research topic in recent years. There are two main ways to store knowledge graphs: RDF-based storage and graph database-based storage. [0003] Traditional KG-QA methods can be divided into three categories of KG-QA. The first category is semantic parsing: this method is a partial linguistic method. The main idea is to convert natural language into a series of formalized logical forms. The logical form of question semantics, through the corresponding query statement (similar to lambda-Caculus) to query in the knowledge base to get th...

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): G06F16/36G06F16/332G06F16/33
CPCG06F16/367G06F16/3329G06F16/3331
Inventor 陈凯
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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