Method and system for converting simplified and traditional Chinese characters

Abstract

The invention discloses a method and system for converting simplified Chinese characters into traditional Chinese characters. The system for converting the simplified Chinese characters into the traditional Chinese characters comprises a dictionary module, an input module, a conversion module and an output module, the dictionary module is used for storing a mapping dictionary and a simplified and traditional character mapping dictionary which are defined by a user, the input module is used for inputting simplified character strings to be converted, the conversion module is used for carrying out sentence division and word division on the simplified character strings in sequence and converting obtained simplified words into traditional words, and the output module is used for combining all the traditional words to form traditional character strings for output. In the word division process, a bidirectional maximum matching algorithm with a forward maximum matching algorithm and a backward maximum matching algorithm combined is adopted, the forward weight of a forward word division result and the backward weight of a backward word division result are calculated, the larger weight is used as the finial word division result, and when the weights are equal, the backward word division result is used as the finial word division result. The method and system achieve the conversion on different expression ways of the same object, and the word division result is more accurate.

Description

technical field [0001] The present application relates to the technical field of language processing, in particular to a method and system for mutual conversion between simplified and traditional Chinese characters. Background technique [0002] With the development of digitization and informatization, communication has become more and more important, and communication through electronic files has become an important means for people to communicate with each other. Due to historical reasons, some of the original traditional Chinese characters have been simplified to form the simplified Chinese characters currently used in mainland China. Thereby resulting in the objective reality that Chinese characters exist in both simplified and traditional writing forms. For example, in mainland China and Singapore, although traditional Chinese characters are occasionally used, simplified Chinese characters are used in most cases; while in Taiwan, Hong Kong and Macau, the original tradi...

AI Technical Summary

Problems solved by technology

[0006] This application provides a method and system for mutual conversion between simplified and traditional Chinese characters to solve the problem of inaccurate word segmentation caused by only using the forward maximum matching algorithm for word segmentation in the prior art, and the inability to solve the problem of inaccurate word segmentation between simplified and traditional Chinese characters. The problem of converting the different terms brought about by the translation habits of loanwords

Images