Document-level sentiment classification method based on dynamic word vectors and hierarchical neural network

A neural network and emotion classification technology, applied in biological neural network models, text database clustering/classification, neural architecture, etc., can solve problems such as feature information loss

Active Publication Date: 2020-02-07
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Second, many deep learning-based models process the entire document at one time, and feature information will be lost when the document is too long

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
  • Document-level sentiment classification method based on dynamic word vectors and hierarchical neural network
  • Document-level sentiment classification method based on dynamic word vectors and hierarchical neural network
  • Document-level sentiment classification method based on dynamic word vectors and hierarchical neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0080] A document-level sentiment classification method based on dynamic word vectors and hierarchical neural networks, such as figure 1 shown, including the following steps:

[0081] S1. Obtain high-quality dynamic word vectors by constructing and training a two-way language model; high-quality dynamic word vectors are word vectors related to the semantics of the sentence where the word is located; including the following steps:

[0082] S1.1. Construct and train a bidirectional language model;

[0083] like figure 2 As shown, the two-way language model is a two-layer language model, and each layer is composed of a two-way long-term short-term memory neural network biLSTM. The language model uses sentences as input units, and the sentences are input to the first-layer language model at the input layer. In order to calculate the probability of the sentence appearing, and the probability of the sentence is obtained by calculating the cumulative multiplication of the probabil...

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 document-level sentiment classification method based on dynamic word vectors and a hierarchical neural network. The method comprises the following steps: obtaining a high-quality dynamic word vector by constructing and training a bidirectional language model; and inputting the obtained dynamic word vector into a hierarchical neural network to model the document, thereby obtaining a vector representation containing rich semantic information, and inputting the vector into a softmax function to classify the document. According to the sentiment classification method, thehigh-quality dynamic word vector is generated by adopting the bidirectional language model, and the hierarchical neural network is provided for modeling the document, so that the problem of insufficient semantic expression of the static word vector to the polysemy is solved, and the document modeling capability in the sentiment classification task is further improved.

Description

technical field [0001] The invention belongs to the field of natural language processing, in particular to a document-level sentiment classification method based on dynamic word vectors and hierarchical neural networks. Background technique [0002] Sentiment classification is one of the important tasks in the field of natural language processing and has a wide range of applications, including e-commerce website comment analysis, public opinion analysis and prediction, etc. The purpose of the document-level sentiment classification task is to predict the sentiment polarity of the document. Traditional methods use tf-idf, SVM and Bayes (Eibe Frank and Remco R Bouckaert. Naivebayes for text classification with unbalanced classes. In European Conference on Principles of Data Mining and Knowledge Discovery, pages 503–510. Springer, 2006.) and other algorithmic modeling documents (Bo Pang, Lillian Lee, and Shivakumar Vaithyanathan. Thumbsup?: sentiment classification using mach...

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): G06F16/35G06F40/30G06F40/279G06N3/04
CPCG06F16/353G06N3/048G06N3/044G06N3/045Y02D10/00
Inventor 刘发贵郑来磊
Owner SOUTH CHINA UNIV OF TECH
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