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

Abstract

The embodiment of the invention belongs to the field of artificial intelligence, and relates to a text error correction method which comprises the following steps: acquiring a target text, calculating a feature vector of the target text, and calculating pinyin features and stroke features of the target text; fusing the feature vector and the pinyin feature to obtain a first target feature, calculating a homophone error probability according to the first target feature, and performing information filtering based on the homophone error probability to obtain a pinyin filtering vector; fusing the feature vector and the stroke feature to obtain a second target feature, calculating a stroke error probability according to the second target feature, and performing information filtering based on the stroke error probability to obtain a stroke filtering vector; and performing feature fusion on the feature vector, the pinyin filtering vector and the stroke filtering vector to obtain a third target feature, inputting the third target feature into a target coding network, and coding to obtain an error correction text. The invention further provides a text error correction device, computer equipment and a storage medium. According to the invention, accurate error correction of the text is realized.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a text error correction method, device, computer equipment and storage medium. Background technique [0002] In the process of text recognition, there are often errors of similar words or homophones caused by OCR recognition or input method. For example, "enter" is written as "enter", "landscape" is written as "fanjing", and "cantaloupe" is written as "Cantaloupe" and other errors. In addition, in the speech recognition scenario, there is also a problem that speech recognition is parsed into similar words or phonetic words. The text error correction task is usually used to detect and correct typos in the input text, which can greatly reduce the errors of similar words and sounds similar to words. [0003] With the development of computer technology, more and more researchers have conducted research on Chinese text error correction, such as the Sof...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiment of the present application is to propose a text error correction method, device, computer equipment and storage medium to solve the technical problem of low text error correction accuracy

Images