Research on English Translation Language Based on Bi-GRU Network

Abstract

The use of neural machine algorithms to translate English is a hot research topic at present. Using the traditional sequential neural framework for English translation has its own limitations in capturing long-distance information. Aiming at the shortcomings of traditional machine translation algorithms, this paper establishes an attention encoding and decoding model, and combines the attention mechanism with the GRU neural network framework, which proves that the performance of the proposed algorithm model is significantly improved compared to the traditional model. Selecting the semantic error to construct the objective function during training can well balance the influence of each part of the semantics, and fully consider the alignment information, providing powerful guidance for the training of deep recurrent neural networks. Experiments show that the English translation model based on recurrent neural network has high effectiveness and stability.