Simulation of Machine-Aided Translation Model Based on Artificial Neural Network Algorithm

In recent years, neural machine translation has achieved rapid development, and replaced the traditional statistical machine translation, becoming the mainstream paradigm in the application and research of machine translation. The translation fluency of the neural machine translation model is high, but there are some problems such as low translation accuracy, easy over-translation/over-translation, low interpretability of the model, and difficult translation of long sentences. In this context, more and more efforts are made to improve the performance of the neural machine translation model by using linguistic knowledge. From the perspective of artificial intelligence, this paper introduces Artificial neural network(ANN) to study Chinese-English machine translation of process language in order to improve the speed and efficiency of translation; At the same time, the integrated BP network model is given, and the network structure, parameter processing, learning algorithm, learning samples and other issues are discussed in detail. The experimental results show that under the premise of character level input, the effect of the CANN-embed model in this project has been further improved compared with the ANN-embed and ANN-search models.