Text processing method, text processing equipment and computer readable storage medium

Abstract

The embodiment of the invention provides a text processing method, text processing equipment and a computer readable storage medium, and the text processing method comprises the steps that an input initial text is checked, and wrong characters and context paragraphs of the wrong characters are determined; based on the wrong character and the context paragraph of the wrong character, determining fusion feature data; a correction candidate set is determined based on the wrong characters, and the correction candidate set comprises a plurality of correction candidate characters; based on the fused feature data, respectively determining the matching degree between each correction candidate character in the correction candidate set and the context paragraph; and determining a correction result of the wrong character based on the matching degree of each correction candidate character in the correction candidate set. By adopting the scheme, the text correction can be automatically carried out, and the processing efficiency and accuracy of the text correction are improved.

Description

technical field [0001] The embodiments of this specification relate to the technical field of natural language processing, and in particular, to a text processing method, a text processing device, and a computer-readable storage medium. Background technique [0002] In the writing process, typos are relatively common mistakes that require correction and correction of the text. At present, text correction schemes mainly include: manual correction schemes and correction schemes based on neural network models. [0003] However, for the manual correction scheme, personnel with certain language skills are required to perform manual correction, which is slow, and human factors can easily affect the correction result. However, the current correction scheme based on the neural network model takes time to train the neural network model, and because the neural network model is only trained on how to confirm the correspondence between the wrong text and the correct text, it is difficu...

AI Technical Summary

Problems solved by technology

[0003] However, for the manual correction scheme, personnel with certain language skills are required to perform manual correction, which is slow and human factors can easily affect the correction results

However, the current correction scheme based on the neural network model takes time to train the neural network model, and because the neural network model is only trained on how to confirm the correspondence between the wrong text and the correct text, it is difficult to face complex and changeable error situations. , the trained neural network model is difficult to adapt, resulting in a high false detection rate

[0004] Therefore, the existing text correction schemes all have the problems of low efficiency and low accuracy

Images