Chinese grammar correcting method and system on basis of XLM (Extensible Markup Language) rule

Abstract

The invention relates to a Chinese grammar correcting method on the basis of an XLM (Extensible Markup Language) rule, which comprises the following steps of: determining a detected Chinese text, i.e. determining the detected Chinese text through inputting or selecting; carrying out word segmentation and labeling parties of speech, i.e. decomposing the determined detected Chinese text into words and / or phrases and respectively labeling the parties of speech for the decomposed words or / and phrases; carrying out circular detection, i.e. according to the parties of speech, characters and positional relations of the words or / and the phrases labeled with the parties of speech, matching the words or / and the phrases labeled with the parties of speech with a Chinese grammar error rule in a Chinese grammar error rule database which is established on the basis of an XML and obtaining a matching result; and displaying the matching result, i.e. displaying the matching result or a modification suggestion corresponding to the matching result. The Chinese grammar correcting method has the advantages that the database has low data capacity and is convenient to maintain; the Chinese grammar correcting method is particularly suitable for establishing the database in an open-ended mode; and the Chinese grammar correcting method has wide Chinese grammar error detection range and high accuracy.

Description

technical field [0001] The present invention relates to a Chinese grammar correction method and system based on XML rules, which mainly uses Chinese word segmentation and part-of-speech tagging and Chinese grammar error correction technology to correct polyphonic character errors, fonts, word forms, grammar, syntax, etc. input by users. Errors, to solve the types of character substitution errors, multi-word / missing word errors, and character position errors during the user's input process. On this basis, the basic functions, Chinese error correction technology, Chinese part-of-speech independent judgment technology, XML rule cycle detection and matching, related prompt technology, etc. are expanded, and the intelligent error correction function is more perfect to provide users with better services. Background technique [0002] With the development of the information society, computers have been widely used to process various Chinese documents based on Chinese characters. U...

AI Technical Summary

Problems solved by technology

The second is that the detection scheme relying on pinyin does not consider the relationship between the context and the words, and the correct words with the same pronunciation and different characters will be provided to the user at the same time, lacking an accurate matching relationship (between the wrong word and the correct word), causing users trouble

The root cause of the inability to judge in the prior art is that there is no effective means to judge whether the words are correct or not when there is no correct word to provide comparison, let alone judge the grammatical error when the words are correct

The third is that the vocabulary of Chinese is very large, and the speed of updating new words and online words is very fast nowadays. The existing lexicons and indexes based on dictionaries and / or correct words based on text statistical information, such lexicons and index tables not only A certain maintenance cost is required, and with the rapid development of the Internet and natural language, it is becoming more and more difficult to correct errors only by dictionaries and / or the collection scale based on text statistical information to meet the needs of Chinese error correction methods. The default words Insufficient library to contain all vocabulary

Images