Text error correction method, device and equipment and readable storage medium

Abstract

The invention provides a text error correction method, device and equipment and a readable storage medium, and the method comprises the steps that description information of a to-be-corrected text is acquired, and the description information is used for representing field information and identification information of the to-be-corrected text; an error correction dictionary is determined according to the description information, the error correction dictionary is a directed word pair set composed of source words and target words, and different description information corresponds to different error correction dictionaries; and performing text error correction on the to-be-corrected text according to the error correction dictionary. Through the method, the effect of improving the correctness and certainty of a text error correction result can be achieved.

Description

technical field [0001] The present application relates to the field of computer information technology, in particular, to a text error correction method, device, equipment and readable storage medium. Background technique [0002] With the rapid development of computer information technology, voice input, handwriting input, scanning input, etc. are often combined with automated systems to complete more complex tasks. But this also puts forward higher requirements on the accuracy of the input, and wrong input will cause the downstream automation system to not work properly. [0003] Without distinguishing the field corresponding to the edited content, blindly performing text error correction leads to poor error correction effect in machine input and specific scenarios. Moreover, the existing schemes generally use a probability model, and the error correction effect is related to the context, which cannot support the requirement that a specific word must be corrected to a spe...

AI Technical Summary

Problems solved by technology

But this also puts higher requirements on the accuracy of the input, and wrong input will cause the downstream automation system to fail to work properly

[0003] Do not distinguish the field corresponding to the edited content, and blindly perform text error correction, resulting in poor error correction effect in machine input and specific scenarios

Moreover, the existing schemes generally use a probabilistic model, and the error correction effect is related to the context, which cannot support the requirement that specific words must be corrected to specific content

Images