Mongolian-Chinese machine translation method based on neural network Turing machine

Abstract

A Mongolian-Chinese machine translation method based on a neural network Turing machine comprises the following steps: firstly, preprocessing Mongolian-Chinese bilingual corpus, vectorizing the Mongolian-Chinese bilingual corpus, and constructing a bilingual dictionary on the basis of the Mongolian-Chinese bilingual corpus; secondly, further expanding storage through a neural network totem machine(NTM), expanding from an internal memory unit of the LSTM to an external memory, introducing a memory mechanism, realizing semantic relation extraction, and giving a semantic relation between two entity words; and finally, searching an optimal solution through decoder model training. Compared with the prior art, according to the invention, semantic analysis is carried out by means of a neural totem machine; related semantic knowledge is found out and extracted, the accuracy of natural language processing is greatly improved by means of the semantic knowledge, corpora are preprocessed by meansof parallel work of a CPU and a GPU, the speed is increased by nearly one time, and the overall translation quality is further improved.

Description

technical field [0001] The invention belongs to the technical field of machine translation, in particular to a Mongolian-Chinese machine translation method based on a neural network Turing machine. Background technique [0002] With the vigorous development of a series of network services including information technology, natural language processing, especially machine translation, plays a vital role in the development of the Internet. Many large search companies and service centers such as Google and Baidu have conducted large-scale research on machine translation, making unremitting efforts to obtain high-quality translations of machine translation. [0003] However, with the continuous efforts of scientists and linguists for decades, problems that cannot be ignored have also been exposed in the process of machine translation development - ambiguous word processing, unregistered word processing, and coding confusion caused by differences in bilingual structure. The transl...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above-mentioned problems such as missing translations, mistranslations, and unregistered word processing in the translation process mainly existing in the above, the purpose of the present invention is to provide a Mongolian-Chinese machine translation method based on neural network Turing machines, aiming at data in small corpus The problem of scarcity and small dictionary can ensure the quality of translation service for users under the condition of reducing system complexity and visualizing the system structure for users, so as to improve the Mongolian-Chinese machine translation system and achieve the goal of better translation

Images