Text error correction method, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention relates to the technical field of computers, and discloses a text error correction method, electronic equipment and a computer readable storage medium. The method includes segmenting a vocabulary to be corrected according to the word granularity to obtain a plurality of retrieval segments, with the types of the retrieval fragments being a single letter or Chinese character pinyin; in a preset index lexical element set, determining a target index lexical element consistent with the retrieval fragment, with the types of the index lexical elements in the index lexical element set comprising single letters and Chinese character pinyin; retrieving in a preset index according to the target index lexical element to obtain a plurality of proper nouns consistent with the target index lexical element in sequence as candidate words; calculating an editing distance according to the word frequency of the vocabulary to be corrected and the word frequency of the candidate words, and scoring the candidate words to obtain scores corresponding to the candidate words; utilizing the candidate word with the highest score as an error correction result to replace the vocabulary to be corrected. The cost of text error correction can be remarkably reduced, the accuracy of text error correction is greatly improved, and meanwhile, the precision of text error correction is improved.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, and in particular to a text error correction method, electronic equipment, and a computer-readable storage medium. Background technique [0002] Natural language processing is an important direction in the field of computer science and artificial intelligence. Natural language processing is a science that integrates linguistics, computer science, and mathematics. It can realize effective communication between humans and computers using natural language. Natural language processing technology is mainly used in machine translation, public opinion monitoring, automatic summarization, opinion extraction, text recognition, text semantic comparison, text error correction, Chinese optical character recognition (Optical Character Recognition, referred to as: OCR), etc., among which, Text error correction refers to the process of correcting erroneous content in the text. Text...

AI Technical Summary

Problems solved by technology

[0003] However, the inventor found that in general text error correction, such as the technical solution disclosed in the patent application number "CN202010164805.5", most of the texts to be processed are first segmented according to the granularity of words, and then the results after segmentation Perform error correction according to word granularity. The error correction result of this method depends on the segmentation result, and the segmentation result depends on the segmentation method. If the segmentation method is not suitable, it will lead to errors in the final error correction result; and , segmenting according to word granularity depends on the corresponding vocabulary dictionary, so the vocabulary dictionary needs to be maintained for a long time, which leads to high cost of text error correction; at the same time, traditional scoring rules usually use edit distance for calculation, and edit distance Generally, the cost of replacement, addition, and deletion is set to 1, and it is impossible to distinguish approximately wrong inputs, which leads to a relatively low accuracy of the final error correction result

Images