A machine translation method and system based on generative adversarial neural network

Abstract

The invention belongs to the field of computer technology, and discloses a method and system for machine translation based on generating a confrontational neural network. The method includes: on the basis of the original machine translation generating network, introducing a discriminant network against the original machine translation generating network; Judging whether the translation of the target language comes from the training parallel corpus, or the result of network machine translation generated by the original machine translation; the discriminant network adopts a multi-layer perceptron feed-forward neural network model to realize binary classification; the system includes: discriminant network, generative network , monolingual corpus, parallel corpus. While making full use of the bilingual parallel corpus resources marked manually, the present invention can also make full use of the monolingual corpus resources for semi-supervised learning; the monolingual corpus resources are very rich and easy to obtain, and solve the training corpus required by the neural network machine translation model Not enough of this puzzle.

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