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

A method for locating near-word errors in text shapes

A positioning method and a technology of shape-like characters, which are applied in the fields of electrical digital data processing, special data processing applications, instruments, etc., can solve problems such as text shape-like word errors, speed problems, and accuracy of word segmentation results, and save time. Effect

Active Publication Date: 2018-12-28
KUNMING UNIV OF SCI & TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a positioning method for text shape and near-word errors, which is used to solve the speed problem and the accuracy of word segmentation results caused by word segmentation during text error detection, eliminating the need for word segmentation and calculation The time consumed by probability can quickly locate the error position in the text, paving the way for the next proofreading work

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 method for locating near-word errors in text shapes
  • A method for locating near-word errors in text shapes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] Embodiment 1: as Figure 1-2 As shown in Fig. 1, a method for locating errors in text shapes and near characters, first divides the long sentence into n short sentences with a length of m, and then uses the Chinese character shape and near word library to find out the shape and near characters corresponding to each word in each short sentence. Words, and form a candidate word vector with the original character, use the commonly used character library to remove the uncommon words in the vector, and form a candidate matrix with the candidate word vectors of all words, so as to obtain the candidate word matrix of each short sentence; Adjacent vectors in a matrix are bundled into words, and the combined correct words are added to the word set w, and the vectors that cannot be combined into words are extracted and the stop words in it are added to the stop word set d; Extract the words in the connecting part of a short sentence and combine them. If there are words, add them ...

Embodiment 2

[0040] Embodiment 2: a kind of positioning method for text shape near word error, the concrete steps of described method are as follows:

[0041] Step1. Establish a database, which includes font library X, corpus Y, commonly used font library Q, and disabled thesaurus T.

[0042] Step2, select the sample sentence A to be processed, such as 'I can't believe my eyes. ’ The wrong character is sunny (eye).

[0043] Step3. Sentence A is preprocessed, and the punctuation marks in the sentence are removed to obtain a new character string. B='I can't believe my eyes' n=11 is the length of character string B.

[0044] Step4. Divide B='I can't believe my eyes' with length m=5, g={n / m}, (n / m) means the smallest integer not less than this number, then g=3 , then L=[L 1 L 2 L 3 ]=['I can't believe it','Believe in my own eyes','Sunny'],L 1 , L 2 length 5, L 3 has a length of 1.

[0045] Step5, find out L respectively 1 , L 2 , L 3 The candidate word vector matrix, such as L 1 T...

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 relates to a positioning method for text shape near-word errors, belonging to the technical field of natural language processing. At first, the long sentence is divided into several short sentences, then, the Chinese character near-shape library is used to find out the near-shape character corresponding to each character in each short sentence, and the candidate character vector is formed with the original character, and the unusual characters in the vector are eliminated by using the common character library, and the candidate character vector of all characters is formed into acandidate matrix, so as to obtain the candidate character matrix of each short sentence; secondly, the adjacent vectors in each candidate matrix are bundled into words, and the combined correct wordsare added into the word set, and the vectors that cannot be combined into a compound word are extracted and added into the deactivated word set; then extracting the characters of the connecting partsof the adjacent two short sentences, combining the characters, and adding the characters to the word set if the words exist are performed; finally, the words in the word set and the deactivated word set are compared with the original text, and these words are eliminated, leaving the wrong words in place.

Description

technical field [0001] The invention relates to a method for locating near-character errors in text, and belongs to the technical field of natural language processing. Background technique [0002] At present, due to the application of OCR text recognition technology, when translating paper texts into computer texts, some texts are often misrecognized and recognized as other characters, and most of these characters are close characters of the original characters. In a large amount of text proofreading, it is a prerequisite for text proofreading to quickly find out the position of typos in the text. [0003] Using N-gram to locate the error position in the text through the connection strength of the context is a common method for text error detection and proofreading. Word segmentation is a prerequisite for using N-gram, but for word segmentation, the accuracy of word segmentation has a great impact on the error detection of text. It plays a decisive role. Word segmentation ...

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): G06F17/27G06F17/30
CPCG06F40/247G06F40/211
Inventor 邵玉斌王林坪龙华杜庆治
Owner KUNMING UNIV OF SCI & TECH