Text translation method and device, electronic equipment and storage medium

Abstract

The invention discloses a text translation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-processed text, and determining a source language and a target language for translating the to-be-processed text; extracting to-be-translated numbers in the to-be-processed text, wherein the to-be-translated numbers comprise at least one of numbers represented by a source language and Arabic numerals; according to a preset standard corresponding to the source language, normalizing the to-be-translated number to obtain a processed number; converting the processed number from the source language to the target language according to the numerical value types of the processed number to obtain target number in the target language. Standardization processing corresponding to the source language is performed on the number to be translated to obtain normative number to be translated, so that translation among various languages and various types of numbers can be realized, and the accuracy of number translation is improved.

Description

technical field [0001] The present disclosure relates to the technical field of data processing, and in particular to a text translation method and device, electronic equipment, and a storage medium. Background technique [0002] In the process of text translation, since numbers usually contain key information in the text, the accuracy of digital translation is very important, especially in fields such as finance and technology. [0003] Usually, neural network-based methods or rule-based methods are used for digital translation. However, the neural network-based digital translation method requires a large amount of labeled training data for translation model training, which increases the system cost, and the inter-translation between different languages ​​requires a large number of translation models, and each translation model has a huge number of parameters. It needs to occupy a large amount of machine resources, but also increases the operation and maintenance costs. C...

AI Technical Summary

Problems solved by technology

However, the neural network-based digital translation method requires a large amount of labeled training data for translation model training, which increases the system cost, and the inter-translation between different languages ​​requires a large number of translation models, and each translation model has a huge number of parameters. Need to occupy a lot of machine resources, but also increase the cost of operation and maintenance

Compared with the neural network-based digital translation method, the rule-based digital translation method reduces the system cost and reduces the occupation of machine resources. However, this translation method does not build a complete translation system for digital translation between languages. For some types or ranges of numbers, it is Does not support translation and is prone to translation errors

Images