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

Text classification method based on capsule network

A text classification and capsule technology, applied in the field of text classification based on capsule network, can solve the problems of low overall accuracy, ignoring the relationship between text parts and the whole, low model training efficiency, etc., and achieve the effect of improving accuracy

Inactive Publication Date: 2019-07-23
JILIN UNIV
View PDF8 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The technical problem to be solved by the present invention is to overcome the existing problems of low overall accuracy, low model training efficiency, neglect of the relationship between the text part and the whole, etc., and propose a text based on EM routing matrix capsule network Classification

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
  • Text classification method based on capsule network
  • Text classification method based on capsule network
  • Text classification method based on capsule network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Below in conjunction with accompanying drawing, the present invention is described in detail:

[0063] The technical problem to be solved by the text classification method based on the EM routing matrix capsule network of the present invention is to overcome the deficiencies in the prior art, and propose to use a new capsule network combined with the EM routing algorithm to solve the text classification problem, considering the variety of text data and ambiguity, use the high-dimensional feature representation of matrix capsules to represent text feature information, perform multi-window and multi-convolution kernel operations in the multi-layer convolutional network layer, and extract important text information. , the capsules are grouped by protocol routing mechanism using EM routing algorithm to form a part-whole relationship. The fully connected capsule network layer maps the text features to the sample distribution space, and performs text classification on the pro...

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 text classification method based on a capsule network. The problems that in the prior art, the overall precision is not high, the applicability is not high, a large amount ofimportant information is lost in the feature extraction process, and the relation between the local part and the overall part in a text is ignored are solved. The method comprises the following steps: 1, nodes in a capsule network being capsules consisting of a group of neurons, executing complex internal calculation on input by using matrix capsules, outputting instantiation parameters from results in a matrix form, and meanwhile, outputting an activation value of each capsule is output; 2, calculating between two adjacent layers in the capsule network through an EM routing algorithm; representing a higher-dimensional concept through Gaussian cluster, and each activation capsule selecting a capsule of the next layer as a father node through an iterative routing process, so that link prediction is realized between two adjacent layers of networks; and 3, training a weight parameter of the full connection layer, and calculating the prediction probability of the real label by using a softmax activation function.

Description

technical field [0001] The present invention relates to a method for solving a text classification problem using a capsule network neural network architecture, more precisely, the present invention relates to a text classification method based on an EM routing matrix capsule network. Background technique [0002] Capsule network, as a new neural network, has received extensive attention after it was proposed, which provides rich information for deep neural network learning and modeling. The task of text classification is to determine the category of the text according to the feature information of the sentence. Common applications include spam recognition, sentiment analysis, relationship extraction, etc. The main directions of text classification tasks include binary classification, multi-classification, and multi-label classification. Due to the natural language With strong ambiguity and diversity, how to deal with ambiguity and diverse output makes it extremely challengin...

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
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/045G06F18/214G06F18/24
Inventor 王英于尤婧王鑫孙小婉孙玉东凌云志马涪元
Owner JILIN 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