Social Text Dependency Syntax Analysis System Based on Deep Neural Network

A deep neural network, social text technology, applied in the field of computer information processing, can solve the problem of sparse social text data

Active Publication Date: 2022-06-21
HARBIN UNIV OF SCI & TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a social text dependency syntax analysis system based on a deep neural network for the problem of sparse social text data in the prior art

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
  • Social Text Dependency Syntax Analysis System Based on Deep Neural Network
  • Social Text Dependency Syntax Analysis System Based on Deep Neural Network
  • Social Text Dependency Syntax Analysis System Based on Deep Neural Network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0030] Specific implementation mode 1: refer to figure 1 To specifically describe this embodiment, the deep neural network-based social text dependency syntax analysis system described in this embodiment includes: a social text crawling module, a preprocessing module, a base bilinear attention module, and a stacked bilinear attention module. force module and joint decoding and training module;

[0031] The social text crawling module is used for crawling social text from social media websites;

[0032] The preprocessing module is used for filtering the obtained social text and generating the initialization word vector;

[0033] The base bilinear attention module is used for pre-training with regular text;

[0034] The stacked bilinear attention module is used to predict social text;

[0035] The joint decoding and training module is used to calculate the empirical risk function for the stacked bilinear attention module, adjust parameters by back-propagation gradient, fit th...

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

A social text dependency syntax analysis system based on a deep neural network, involving the field of computer information processing technology, aimed at the problem of sparse social text data in the prior art, including: social text crawling module, preprocessing module, and basic bilinear attention module , a stacked bilinear attention module and a joint decoding and training module; the social text crawling module is used to crawl social text from social media sites; the preprocessing module is used to filter the obtained social text , and the generation of initialization word vectors; the base bilinear attention module is used for pre-training with regular text; the stacked bilinear attention module is used for predicting social text; the joint decoding and training The module is used to calculate the empirical risk function of the stacked bilinear attention module, and perform backpropagation gradient adjustment parameters, fit the training function, and finally use GPU parallel computing to accelerate model training.

Description

technical field [0001] The invention relates to the technical field of computer information processing, in particular to a social text-dependent syntax analysis system based on a deep neural network. Background technique [0002] Dependency analysis is a basic and important task in natural language processing, and many applications need to perform dependency analysis on sentences to provide syntactic results for corresponding tasks. Through the powerful computing power of the computer, the dependent syntactic structure of the sentence is identified. Dependency syntax trees are roughly divided into two categories according to their structure: Project and Non-project dependency syntax structures; according to decoding algorithms: Graph-based and Transition-based dependencies algorithm. The deep neural network partially overcomes the gradient dispersion and explosion of the traditional neural network, and has developed rapidly in recent years, and has made great progress in v...

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 Patents(China)
IPC IPC(8): G06F40/211G06F40/284G06F16/951G06N3/04G06N3/08
CPCG06F16/951G06N3/084G06N3/044G06N3/045
Inventor 刘宇鹏张晓晨
Owner HARBIN UNIV OF SCI & 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