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

Sentence noise design method and device and computer storage medium

A design method and noise technology, applied in computing, neural learning methods, instruments, etc., can solve the problem of low fluency of noisy text

Active Publication Date: 2021-02-19
PENG CHENG LAB
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In view of this, a sentence noise design method, equipment and computer storage medium are provided to solve the problem of low fluency of noise text

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
  • Sentence noise design method and device and computer storage medium
  • Sentence noise design method and device and computer storage medium
  • Sentence noise design method and device and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0071]Referencefigure 2 ,figure 2 This is the first embodiment of the sentence noise design method of the present invention, and the method includes:

[0072]Step S110: Preprocessing the original text to generate a first noise text.

[0073]The original text can be a text in a pre-loaded corpus or a text in any corpus, which is not limited here.

[0074]Preprocessing may be a preparation process performed before the original text generates the first noise text.

[0075]The first noise text may be a text formed by adding noise words to the original text, and the first noise text also provides position information of the noise words in the first noise text for subsequent fluency processing.

[0076]Step S120: Perform fluency optimization processing on the first noisy text to obtain a second noisy text whose fluency meets a preset condition.

[0077]The fluency optimization process is mainly optimized from the aspects of part of speech and word form. When the first noise text that has performed the flue...

no. 2 example

[0155]ReferencePicture 11 ,Picture 11 This is the second embodiment of the sentence noise design method of the present invention, and the method further includes:

[0156]Step S210: preprocessing the original text to generate a first noise text.

[0157]Step S220: Perform fluency optimization processing on the first noise text to obtain a second noise text whose fluency meets a preset condition.

[0158]Step S230: Predict the second noise text using a deep learning model, and if the predicted value is different from the predicted value of the original text using the deep learning model, then use the second noise text as a target result.

[0159]Step S240: If the predicted value is the same as the predicted value of the original text using the deep learning model, re-execute the process of generating the first noise text.

[0160]The predicted value is the same as the predicted value of the original text using the deep learning model, indicating that the fluency optimization processing effect is no...

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 sentence noise design method and device and a computer storage medium, and the method comprises the following steps: carrying out the preprocessing of an original text, generating a first noise text, executing fluency optimization processing on the first noise text to obtain a second noise text with fluency meeting a preset condition, predicting the second noise text by adopting a deep learning model, and taking the second noise text as a target result if the prediction value is different from the prediction value of the original text by adopting the deep learning model. According to the method, the problem that the fluency of the noise text is not high is solved, and a generated noise fluency optimization algorithm is added on the basis of iterative mode positioning and noise word injection attacks, so that the generated noise text better conforms to correct grammars and human reading habits.

Description

Technical field[0001]The invention relates to the field of natural language processing, in particular to a method, equipment and computer storage medium for designing sentence noise.Background technique[0002]Anti-sample refers to deliberately adding subtle interference to the input sample, causing the model to output a high-confidence error result. It has achieved some results in the image and speech fields. However, in the text field, due to its discrete nature, it still faces many challenges . For the natural language processing attack model, it is not only necessary to be able to deceive the target model, but also to meet three attributes for the generated adversarial samples[0003](1) Human prediction consistency, that is, human predictions of the input text remain unchanged;[0004](2) Semantic similarity, the generated adversarial samples should be as similar to the original text as possible.[0005](3) Sentence fluency, the generated text should be read naturally and grammatically...

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): G06F40/247G06F40/211G06F40/194G06F40/289G06N3/04G06N3/08
CPCG06F40/247G06F40/194G06N3/08G06F40/211G06F40/289G06N3/044G06N3/045
Inventor 杨孙傲钟晓雄张伟哲周颖程正涛
Owner PENG CHENG LAB