Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Text error correction method and device based on artificial intelligence recurrent neural network

A cyclic neural network and artificial intelligence technology, applied in the computer field, can solve the problems of sparse data, inability to reach users, and poor error correction accuracy, and achieve the effect of improving accuracy, improving user experience, and improving the accuracy of error correction.

Inactive Publication Date: 2017-11-17
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In the above method, the completion of the error correction task depends on the design of features, which is data-driven. The model faces problems such as high data normative requirements, data sparseness and poor model versatility, and cannot be used on a large scale. Due to the lack of contextual syntactic information , making the accuracy of error correction poor and unable to meet user expectations

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
  • Text error correction method and device based on artificial intelligence recurrent neural network
  • Text error correction method and device based on artificial intelligence recurrent neural network
  • Text error correction method and device based on artificial intelligence recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0029] Specifically, each embodiment of the present invention aims at the problem that in the prior art, text error correction methods mainly rely on feature design, are data-driven, and lack syntactic information of context, resulting in poor error correction accuracy, and propose a method based on Text Error Correction with Recurrent Neural Networks for Artificial Intelligence. The text error correction method based on the artificial intelligence cyclic neural network provided by the embodiment of the present invention, after o...

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 provides a text error correction method and device based on an artificial intelligence recurrent neural network. The method comprises following steps: obtaining text data to be corrected; using a trained recurrent neural network model to correct the test text data to be corrected to generate text data after error correction. Therefore, by means of the recurrent neural network model and combined with sentence structure information of a context, text data having errors is corrected, the error correction accuracy is increased and user demand is satisfied and user experience is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a text error correction method and device based on an artificial intelligence-based cyclic neural network. Background technique [0002] Artificial Intelligence (AI for short) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. [0003] With the popularization of Internet technology and the development of artificial intelligence, human life is increasingly dependent on technologies such as search engines, speech recognitio...

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
IPC IPC(8): G06F17/27G06N3/08
CPCG06N3/08G06F40/205G06F40/232G06N3/044G10L25/30G06N3/084G06F40/10
Inventor 杨春杰姚树杰
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More