Chinese-Vietnamese Jointly Training Neural Machine Translation Method Based on Pivot

Abstract

The invention relates to a pivot-based Chinese-Vietnamese joint training neural machine translation method, belonging to the technical field of natural language processing. The present invention includes the steps: firstly, the method uses Chinese-Vietnamese parallel corpus to train the translation model to obtain the word vector representation of Chinese and Vietnamese; secondly, the Chinese-English and English-Vietnamese translation models are jointly trained with English as the pivot language, and then The Chinese-Vietnamese vector representation of the Chinese-English, English-Vietnamese translation model and the Chinese-Vietnamese vector representation obtained by the Chinese-Vietnamese model are optimized for Chinese-Vietnamese joint training. The present invention combines the Chinese-Vietnamese parallel corpus with the Chinese-English and English-Vietnamese parallel corpus for joint training, making full use of the English pivot corpus to improve the performance of Chinese-Vietnamese machine translation, thus solving the problem of poor translation model performance caused by the lack of Chinese-Vietnamese parallel corpus The problem.

Description

technical field [0001] The invention relates to a Chinese-Vietnamese joint training neural machine translation method based on a pivot axis, and belongs to the technical field of natural language processing. Background technique [0002] Machine translation is an effective tool for large-scale language translation. In recent years, the exchanges and cooperation between China and Vietnam have become increasingly close, and machine translation is a more effective way to exchange information across languages. Therefore, it is very important to study Chinese-Vietnamese machine translation. application value. [0003] Neural machine translation is a machine translation method proposed in 2014, and the current mainstream neural machine translation models all use an encoder-decoder architecture. Neural machine translation has achieved good translation performance on language pairs with massively parallel corpora, but in low-resource scenarios, the translation quality of neural mac...

AI Technical Summary

Problems solved by technology

[0006] The invention provides a pivot-based Chinese-Vietnamese joint training neural machine translation method to solve the problem that the translation quality of neural machine translation is lower than that of statistical machine translation in low-resource scenarios; it solves the problem of low resources in Chinese-Vietnamese In terms of language pairing, the scale and quality of the Chinese-Vietnamese parallel corpus lead to poor performance of Chinese-Vietnamese machine translation

Images