Method and device for correcting text

A text and text library technology, applied in the computer field, can solve problems such as inappropriate expression of text, grammatical errors, and inappropriate word collocations

Active Publication Date: 2013-03-27
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF6 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are already technologies for checking text errors, but such errors can usually only detect spelling mistakes or grammatical errors, and cannot correct inappropriate expressions or inappropriate word collocations in the 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
  • Method and device for correcting text
  • Method and device for correcting text
  • Method and device for correcting text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] At first the method provided by the present invention is described, figure 1 The flow chart of the method provided by Embodiment 1 of the present invention, such as figure 1 As shown, the method may include the following steps:

[0061] Step 101: Obtain the text to be corrected.

[0062] In the embodiment of the present invention, the text to be corrected may be a paragraph, a sentence, or a phrase.

[0063] Step 102: Use the preset standard text library to search for similar texts to the above text to be corrected.

[0064] According to different types of texts to be corrected, standard text libraries can be selected in this step. For example, if the text to be corrected is a sentence, the standard text database may be a standard sentence database. More specifically, if it is used for correction of academic papers, the academic paper sample sentence database may be used.

[0065] When looking for similar texts, the similarity between the text to be corrected and th...

Embodiment 2

[0114] image 3 The device structure diagram provided for the second embodiment of the present invention, such as image 3 As shown, the device may include: an input unit 300 , a similar text determination unit 301 , a difference word determination unit 302 , a candidate text determination unit 303 , a fluency calculation unit 304 and a collocation probability calculation unit 305 .

[0115] The input unit 300 acquires text to be corrected.

[0116] In the embodiment of the present invention, the text to be corrected may be a paragraph, a sentence, or a phrase.

[0117] The similar text determination unit 301 uses a preset standard text library to find similar texts of the text to be corrected.

[0118] According to different text types to be corrected, the corresponding standard text library can be selected. For example, if the text to be corrected is a sentence, the standard text library can be a standard example sentence library. More specifically, if it is used for the c...

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 method and device for correcting a text. The method comprises the following steps of acquiring a text to be corrected; searching a similar text of the text to be corrected by using a preset standard text base; comparing the similar text with the text to be corrected to determine different word pairs, wherein the different words of the text to be corrected in the different word pairs are primary words, and the different words in the similar text are candidate words corresponding to the primary words; using the candidate words to respectively substitute the corresponding primary words in the text to be corrected to form M1 candidate texts, wherein M1 is a positive integer; respectively calculating text fluency of the candidate texts and the text to be corrected, and selecting M2 texts of which the fluency is the highest, wherein M2 is a positive integer less than or equal to M1+1; and respectively calculating collocation probability of M2 texts, and selecting M3 texts of which the collocation probabilities are the top three as corrected texts, wherein M3 is a positive integer less than or equal to M2. By the method and the device, sloppy expression or improper collocation in the text can be corrected.

Description

【Technical field】 [0001] The invention relates to the field of computer technology, in particular to a text correction method and device. 【Background technique】 [0002] With the development of society and the advancement of science and technology, international academic exchanges are becoming more and more frequent. When communicating academic documents in non-native languages ​​between countries, especially for inexperienced people, whether the expression is authentic and whether the word collocation is appropriate are often troubled issues. For example, if you want to express "green food" in English, for a person whose mother tongue is Chinese, it is likely to be expressed as "green food", but in fact, the authentic expression should be "organic food". It can be seen that high-quality Academic papers are inseparable from authentic language expressions. [0003] At present, there are technologies for checking text errors, but such errors can usually only detect typos or ...

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): G06F17/27
Inventor 刘占一吴华王海峰
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products