Semi-supervised Mongolian-Chinese neural machine translation method based on collaborative training

Abstract

At present, a decoder-encoder structure is commonly used in neural machine translation, and a good effect is obtained under the condition that parallel corpora are sufficient. However, for the Mongolian language as a small language, mongolian and Chinese parallel corpus resources are limited and are very difficult to obtain, therefore, the invention provides a semi-supervised Mongolian-Chinese neural machine translation method based on collaborative training. Three translation models are constructed by using a semi-supervised classification generative adversarial network: a Mongolian-Chinese translation model M-mo-ch, an English-Chinese translation model M-en-ch and a Korean-Chinese translation model M-ko-ch; the three translation models are used for marking a multi-source end parallel corpus Mongolian and Korean to a target end, namely Chinese, the marked corpus with the best quality is selected by using a language model LM-ch trained by Chinese monolingual training to expand an original corpus, and a better translation model is trained again. According to the method, collaborative training and the semi-supervised classification generative adversarial network are combined and applied to Mongolian-Chinese neural machine translation, and the quality of the Mongolian-Chinese neural machine translation model is improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, relates to machine translation, in particular to a semi-supervised Mongolian-Chinese neural machine translation method based on collaborative training. Background technique [0002] Machine Translation (MT) refers to the process of using computers to automatically convert text from one natural language (source language) into another natural language (target language) with exactly the same meaning. [0003] In recent years, although neural machine translation has gradually replaced traditional statistical machine translation, the performance of translation systems is highly dependent on the quality, scale and domain coverage of parallel corpora. However, due to the lack of high-quality, large-scale, and wide-coverage Mongolian-Chinese bilingual parallel corpora such as Mongolian, neural machine translation does not perform well in the Mongolian-Chinese translation model, and it is ...

AI Technical Summary

Problems solved by technology

However, due to the lack of high-quality, large-scale, and wide-coverage bilingual bilingual parallel corpora such as Mongolian, neural machine translation does not perform well in the Mongolian-Chinese translation model, and it is impossible to obtain better quality Translation results

Images