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

Feature coding method and device, electronic equipment and readable storage medium

A feature encoding and encoding technology, applied in neural learning methods, biological neural network models, semantic analysis, etc., can solve problems such as weak robustness and low accuracy, and achieve the effect of improving robustness

Pending Publication Date: 2020-05-15
IFLYTEK CO LTD
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a feature encoding processing method, device, electronic equipment, and readable storage medium to solve the problems of low accuracy and weak robustness of feature encoding methods 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
  • Feature coding method and device, electronic equipment and readable storage medium
  • Feature coding method and device, electronic equipment and readable storage medium
  • Feature coding method and device, electronic equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0037] In one embodiment of the present invention, a feature encoding method is provided, which is detailed in conjunction with the attached figure 1 To illustrate, feature encoding methods include:

[0038] S100. Obtain a statement to be analyzed.

[0039] Specifically, in this step, the sentence to be analyzed in the form of text may be obtain...

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

Embodiments of the invention provide a feature coding method and device, an electronic equipment and a readable storage medium. The method comprises the steps of obtaining a to-be-analyzed statement;inputting the to-be-analyzed statement into a pre-trained feature coding model to obtain a feature coding result output by the feature coding model; wherein the feature coding model is obtained by jointly training an attention module and a coding module in a trained generative adversarial network model. An attention module and a coding module in a trained generative adversarial network model are utilized to jointly train the feature coding model, so that the robustness of the feature coding model is improved.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a feature encoding method, device, electronic equipment and readable storage medium. Background technique [0002] Semantic understanding is one of the important issues in the field of natural language processing. Its task is to parse natural language into structured, machine-readable feature codes representing semantic information. The robustness of the feature encoding model is an unavoidable problem in the field of semantic understanding, which measures the noise resistance of the feature encoding model. When the content of the output sentence is disturbed, the key features of the sentence extracted by the feature encoding model will be inaccurate, resulting in the machine not being able to understand the true semantics of the sentence. [0003] Enhancing the anti-noise ability of the feature encoding model requires using a large number of noised sentences as traini...

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): G06F40/30G06N3/04G06N3/08
CPCG06N3/08G06N3/045Y02D10/00
Inventor 戴瑾胡加学赵乾宋时德
Owner IFLYTEK CO LTD