Multi-language-pair neural network machine translation method and system

Abstract

The invention belongs to the technical field of computer software and discloses a multi-language-pair neural network machine translation method and system. A plurality of bilingual parallel corpora ofa same language system are utilized and mapped to a same high-dimensional vector space after byte pair encoding, so that multiple languages share a same semantic space, the size of a word list is reduced, model parameters are reduced, and convergence of a model is accelerated. Words of a same language family are in the same vector space, more information can be learned mutually, the information which can not be learned through only certain bilingual parallel corpora can be learnt, and the quality of word vectors is improved. The machine translation system can be used for translation in the language direction without direct bilingual parallel corpora, and the translation quality in the scarce parallel corpus translation direction is greatly improved through mutual information learning. Meanwhile, the same model is used for translation for the translation direction low in utilization rate, occupation of a server is reduced, and the utilization rate of the server is increased.

Description

technical field [0001] The invention belongs to the technical field of computer software, and in particular relates to a neural network machine translation method and system for multilingual pairs. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: [0003] Machine translation is a process of translating one natural language into another natural language using machine learning techniques. As an important branch of computational linguistics, it involves cognitive science, linguistics and other disciplines, and is one of the ultimate goals of artificial intelligence. [0004] The existing mainstream machine translation model uses an encoding-decoding structure based on a self-attention mechanism, which consists of an encoder and a decoder. Both are dominated by the self-attention layer. [0005] The translation process mainly includes: first, map the input word to a high-dimensional vector space to obtain a wor...

AI Technical Summary

Problems solved by technology

[0008] (1) High-quality bilingual parallel corpus is very scarce, especially parallel corpus between minor languages

For machine translation, there is a lack of high-quality bilingual parallel corpus, and it is very difficult to train a usable machine translation system. The translation quality is poor, and the translation performance is poor, especially in terms of fidelity.

Although using English as the interlanguage can solve some problems, the translation effect is not ideal, and the translation speed is doubled

Moreover, a machine translation system can only translate language pairs in one direction, and language pairs that are used infrequently will waste server resources

Images