On this page

A Strategy for Improving the Accuracy of Context-Aware Translation Based on Deep Reinforcement Learning in English Translation

By: Ping Yin 1, Juanyin Liu 1
1Teaching Department of Basic Courses, Hebei Vocational University of Industry and Technology, Shijiazhuang, Hebei, 050091, China

Abstract

The development of globalization has led to increasingly stringent requirements for translation accuracy. This paper designs a cross-language English translation model based on deep reinforcement learning and translation quality assessment, and selects the Transformer architecture with multi-layer encoder-decoders. Through the reward and punishment mechanism of the intelligent NMT system, real-time probability calculations of contextual information are performed to select the most appropriate words at the semantic level as components of the target sentence. Combined with a supervised quality assessment module, the translated text is scored, and the next word selection is guided. Experiments show that after 934 iterations, the BLEU score stabilizes around 97.62%. The F1 score reaches 99.87% after 316 iterations, and the accuracy achieves a stable value of 90.74% after 815 iterations. In two-class cross-language English translation tasks, the model’s average BLEU scores were 90.67% and 93.08%.