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

Remote supervision entity relationship extraction method based on denoising convolutional neural network

A convolutional neural network and remote supervision technology, applied in the fields of natural language processing and entity relationship extraction, can solve problems affecting model performance and other issues

Active Publication Date: 2020-04-28
JIANGNAN UNIV
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method makes the word vector have a richer expression, but in a specific task like relation extraction, some information in the semantic space will become noise, which will affect the performance of the model.

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
  • Remote supervision entity relationship extraction method based on denoising convolutional neural network
  • Remote supervision entity relationship extraction method based on denoising convolutional neural network
  • Remote supervision entity relationship extraction method based on denoising convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] In order to make the purpose, technical solutions and advantages of the present invention clearer, the specific application mode of the present invention is further described in combination with the technical solutions and accompanying drawings given above, wherein the same or similar symbols throughout represent the same or similar elements or have the same or similar components. components with similar functions.

[0061] like figure 1 As shown, it is a flow chart of a remote supervision relation extraction method proposed by the present invention

[0062] The word vector representation, the word vector uses the unsupervised pre-trained word vector, in addition, the location information of the entity is added for the relationship extraction, and the sentence represents X input ={w 1 ,w 2 ,...,w n},in d a is the dimension of the word vector, d b is the dimension of location information. Inputting sentence information into the model first passes through the fea...

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 remote supervision entity relationship extraction method based on a denoising convolutional neural network, and belongs to the field of natural language processing and entityrelationship extraction. The invention provides a denoising convolutional neural network model to extract the relationship of entities. A feature scaling layer is used for effectively scaling the word vector in each semantic space, and meanwhile, attention weight calculation is performed on each convolution kernel in the convolution network, so that the network can learn the importance of different convolution kernels by itself, the influence of noise is further reduced, and the purpose of improving the model extraction capability is achieved.

Description

technical field [0001] The invention belongs to the fields of natural language processing and entity relationship extraction, and proposes a denoising convolutional neural network model, which can effectively analyze the relationship between entity pairs in complex texts, thereby predicting the relationship between entities. Background technique [0002] With the rapid development of the Internet, the network contains a large amount of information, but a lot of information is unstructured and cannot be effectively utilized. In the process of building a knowledge map, structured information is very critical, and how to extract structured data from a large amount of unstructured data is a big problem. As an important task of information extraction, entity relationship extraction refers to the extraction of predefined entity relationships from unstructured text on the basis of entity recognition. The relationship between entity pairs can be formally described as a relational 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): G06F16/36G06F40/211G06F40/295G06F40/30G06N3/04G06N3/08
CPCG06F16/367G06N3/082G06N3/045Y02D10/00
Inventor 宋威朱富鑫
Owner JIANGNAN 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