Machine translation method and system based on generative adversarial neural network

Abstract

The invention belongs to the technical field of computers, and discloses a machine translation method and system based on a generative adversarial neural network. The method comprises the following steps that: on the basis of an original machine translation generation network, a discrimination network which generates network countermeasure with the original machine translation generation network is imported; a translation used for judging a target language is from a training parallel corpus and is a network machine translation result of the original machine translation generation network; and the discrimination network adopts a multi-layer sensor feedforward neural network model to realize binary classification. The system comprises the discrimination network, a generation network, a mono-lingual corpus and a parallel corpus. While manually annotated bilingual parallel corpus resources are fully utilized, and mono-lingual corpus resources also can be fully utilized to carry out semi-supervised learning; and the mono-lingual corpus resources are very rich and can be easily obtained, and the problem that required training corpora required by the neural network machine translation model are not sufficient is solved.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a machine translation method and system based on generating an adversarial neural network. Background technique [0002] Machine translation is the process of using computer algorithms to automatically translate sentences in one source language into sentences in another target language. Machine translation is a research direction of artificial intelligence, which has very important scientific research value and practical value. With the continuous deepening of the globalization process and the rapid development of the Internet, machine translation technology is playing an increasingly important role in domestic and foreign political, economic, social, and cultural exchanges. [0003] At present, the machine translation method based on deep neural network is the best method in the field of machine translation. It mainly adopts the "encoding-decoding" structure, whi...

AI Technical Summary

Problems solved by technology

[0005] The main defect of the existing technology is that the training of the deep neural network model relies heavily on a large-scale manually labeled bilingual parallel sentence pair corpus

Due to the high cost of manual labeling and the lack of large-scale, high-quality manual-labeled bilingual parallel corpora, the training data of the neural network machine translation model is insufficient and the performance is poor, which is the bottleneck problem faced by the existing neural network machine translation model; especially Especially in some small languages, there are very few parallel corpus resources that can be used to train the neural network model, making it difficult to build a high-performance machine translation system

Images