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

Text classification method based on semi-supervised graph convolutional neural network

A convolutional neural network and text classification technology, applied in neural learning methods, biological neural network models, text database clustering/classification, etc., to achieve the effect of solving the sparseness of labeled data

Pending Publication Date: 2021-12-14
NANJING UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Therefore, the existing graph-based methods are used to study how to construct good text representations, most of which are based on the graph structure relationship between words and text, which has limitations.

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 semi-supervised graph convolutional neural network
  • Text classification method based on semi-supervised graph convolutional neural network
  • Text classification method based on semi-supervised graph convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further described below in conjunction with embodiment, but protection scope of the present invention is not limited to this:

[0046] Experimental dataset

[0047]We conducted experiments on four widely used public data, including Subj, SST-2, AGnews, and CR. For all data sets, we only deleted some low-frequency words from the original data set. Next, we will introduce the relevant The dataset, and related statistics are shown in Table 1.

[0048] Table 1 50% split data set statistics

[0049]

[0050] Subj: Sentiment classification data set, whose task is to determine whether the emotion of a sentence is positive or negative, it has 9,000 training samples and 1,000 test samples, in this experiment, this training set is combined with the test machine, according to the number of categories Same, divide it into a training set of 5,000 and a test set of 5,000.

[0051] AGnews: This data set is about Internet news. It contains four categ...

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 semi-supervised graph convolutional neural network, and the method comprises the steps: coding texts into fixed vectors through employing a BERT model in order to construct a semantic relation between the texts, analyzing a similar relation between the texts, and constructing a side relation between documents. The feature representation of the text can depend on similar document features, the neighbor node features of the document nodes are aggregated by using the graph convolutional neural network to perform feature learning, and the feature representation of the target document nodes is enhanced. By adopting the GMMM model, not only can feature learning of the nodes be promoted, but also label information spreading can be performed, and the problem of sparse label data is effectively solved.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a text classification method based on a semi-supervised graph convolutional neural network. Background technique [0002] Natural semantic documents also contain internal graph structures, such as syntactic and semantic analysis trees, which define the syntactic / semantic relationship between words in a sentence. Some researchers have tried to clarify the functional relationship with the help of graph structures. Therefore, some researchers Start to consider the influence of the graph structure in the document on the feature representation of the document. On the other hand, there is also an interaction relationship between documents. Well-known documents with the same semantics have similar distributions, while non-similar documents have different distributions. , that is, it can be speculated that the feature representation of text can depend on similar document features. ...

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): G06F16/35G06F40/126G06N3/04G06N3/08
CPCG06F16/35G06F40/126G06N3/08G06N3/047G06N3/044G06N3/045Y02D10/00
Inventor 曹杰申冬琴陈蕾王煜尧郭翔
Owner NANJING UNIV OF SCI & TECH
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