Context-Aware Translation Accuracy Improvement Strategies Based on Deep Reinforcement Learning in English Translation

Abstract

The field of machine translation has made significant progress in recent years, but how to improve translation accuracy and context consistency is still an urgent challenge. In this paper, a context-aware translation accuracy improvement strategy based on deep reinforcement learning is proposed for English translation. Based on CNNs neural machine translation model, the multi-intelligence deterministic deep policy gradient algorithm is utilized to combine the output of the translation model with the human evaluation index (BLEU), and the reward function is constructed to guide the model learning. In addition, in order to enhance the context-awareness of the model, the study introduces a context encoder in the deep reinforcement learning framework to capture sentence-level contextual information and incorporate it into the translation process. The experimental results show that the optimized model has better training performance, with 40 epochs of iterations, the Loss converges to 0.135 up and down, and its English translation F1 value is 94.95%. And as the number of encoder layers rises, the number of semantic high-level features increases. The N-GRR difference between the generated translation and the standard translation of the model in this paper is the smallest, and the over-translation phenomenon is less. The number of out-of-set word interference is more than 6, and the BLEU value of this paper’s model is improved by 17.89% to 55.55% compared with the comparison model. And the algorithm has good translation performance, with METEOR scores of 0.562~0.803 on different topics. The research results fully verify the effectiveness of deep reinforcement learning based on deep reinforcement learning to improve the accuracy of English machine translation.