Corpus-Driven Deep Learning-Based English-Chinese Translation Model Construction and Its Application to College English Teaching

In this paper, a Chinese-English control corpus is first constructed, and the application of the attention mechanism in the model is explored and investigated using the word-to-word procedure in machine translation with the newstest2023 dataset. In this paper, with the support of the deep neural network Transformer model, the acquired Chinese-English control dataset that meets the test conditions is put into the model for training to get the results of the performance of the attention mechanism, and the BLEU is used to evaluate the accuracy of the translation, and finally, the effect of the application of the dual-driven teaching model in English-Chinese translation is analyzed. The results show that the Encoder-Decoder machine translation model proposed in this paper has a closer connection between words, and the model performs well. In addition. The students in the experimental group have a significant increase of 7.54 points in the mastery of translation theories and skills compared with the control group (t = −9.378, P < 0.05). The mean value of students in the experimental group in English-Chinese translation mastery, and with writing increased significantly by 6.26 points (t=−7.983, p<0.05) and 10.81 points (t=−16.124, p<0.05) than the control group, respectively, and it is obvious that this teaching mode promotes college students’ mastery of English-Chinese translation ability and writing ability in English translation.