Unlock instant, AI-driven research and patent intelligence for your innovation.

The training method, device, equipment and medium of emotion reason to extraction model

A training method and reason technology, applied in the field of neural network model, to achieve the effect of improving the prediction accuracy

Active Publication Date: 2022-04-08
SICHUAN UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The emotion classification task is mainly to classify the emotion of the text, but with the continuous development of natural language processing technology, only the task of emotion classification can no longer meet the needs of real life, so researchers turn their attention to research reason behind emotion

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
  • The training method, device, equipment and medium of emotion reason to extraction model
  • The training method, device, equipment and medium of emotion reason to extraction model
  • The training method, device, equipment and medium of emotion reason to extraction model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.

[0052] The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.

[0053] Hereinafter, the terms "comprising",...

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 embodiment of the present invention discloses a training method, device, device and medium for an emotional reason pair extraction model, which relates to the field of neural network models. The method includes: inputting document samples into the first encoding network to encode words and clauses to obtain emotional clauses Representation and reason clause representation; predict the two clause representations of each clause, and get the two clause prediction results, emotion output and reason output; input the emotion output and reason output to the graph attention network to update; based on the pairing network , get the corresponding emotion representation and reason representation according to the updated two outputs, and pair the emotion representation and reason representation to get the emotion reason pair; according to the prediction network, get the prediction result of the emotion reason pair; calculate the loss value according to the prediction result and update the model . Therefore, the present invention uses the graph attention network to extract the relationship between each clause, which enriches the information contained in the emotion output and reason output of each clause, and improves the accuracy rate.

Description

technical field [0001] The invention relates to the field of neural network models, in particular to a training method, device, equipment and medium for an emotion cause pair extraction model. Background technique [0002] The emotion classification task is mainly to classify the emotion of the text, but with the continuous development of natural language processing technology, only the task of emotion classification can no longer meet the needs of real life, so researchers turn their attention to research The reason behind the emotion. [0003] Therefore, how to determine the emotional words / sentences in the text and the causal words / sentences pointing to the emotional words / sentences is one of the main research directions at present. Contents of the invention [0004] In view of this, the present invention provides a training method, device, equipment and medium for an emotion-cause pair extraction model, which are used to determine the emotion clauses in the text and 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 Patents(China)
IPC IPC(8): G06F40/30G06N3/04G06N3/08
CPCG06F40/30G06N3/08G06N3/044
Inventor 琚生根高德辰周刚
Owner SICHUAN UNIV