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

A Chinese grammatical error detection method based on textualized word vector

A technology for grammatical errors and detection methods, applied in the field of information processing, can solve problems such as poor use of Chinese vocabulary and different meanings

Active Publication Date: 2018-12-07
BEIJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the work did not make good use of the information expressed in Chinese vocabulary, ignoring the fact that the same word may have different meanings in different texts

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
  • A Chinese grammatical error detection method based on textualized word vector
  • A Chinese grammatical error detection method based on textualized word vector
  • A Chinese grammatical error detection method based on textualized word vector

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] Next, embodiments of the present invention will be described in more detail.

[0014] Figure 1 It is a network structure diagram of the error detection method provided by the present invention, which includes:

[0015] Step S1: the text word vectorization of input;

[0016] Step S2: the cyclic neural network forms a mask about the importance of each component in the word vector;

[0017] Step S3: Text matrix reconstruction;

[0018] Step S4: the cyclic neural network extracts context information;

[0019] Step S5: the forward neural network calculates the error score of each word;

[0020] Step S6: use the error score to infer the error location;

[0021] Each step will be described in detail below:

[0022] Step S1: Text word vectorization. The present invention first establishes a mapping dictionary from words to word vector numbers, and maps each word in the text to a corresponding word number. Create a word vector matrix, each row number corresponds to the ...

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 Chinese grammatical error detection method and device, belonging to the information processing field. The characteristics of the method include: firstly, the input text wordsare vectorized and connected to form a text matrix; then, the mask of the importance of each component in the word vector is formed by using the circulating neural network; a text matrix is reconstructed; the context information is extracted by using the loop neural network; the error scores of each word are calculated by using feedforward neural network; the error scores are utilized to infer the wrong location. The method improves the Chinese grammar detection effect by combining the text-based word vector, and has great use values.

Description

technical field [0001] The invention relates to the field of information processing, in particular to a neural network-based Chinese grammatical error detection method. Background technique [0002] Chinese grammatical error detection is a relatively new task in Chinese natural language processing. The purpose is to judge whether the sentences written by non-Chinese native speakers are wrong, and give error messages. [0003] At present, the most common Chinese grammar error detection method is to complete the error detection task as a supervised sequence labeling task. The more common grammatical error detection includes N-Gram, recurrent neural network, etc. However, these networks are very dependent on artificially designed features and require more artificial features to be added. Recently, since the neural network can learn the features of the text by itself to replace the complex artificial features, many works are trying to apply the neural network to Chinese gramma...

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): G06F17/27G06N3/04G06N3/08
CPCG06N3/084G06F40/211G06N3/044G06N3/045
Inventor 李思赵建博李明正徐雅静
Owner BEIJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com