Research on improving machine translation models for translation quality of English literary works

Abstract

This paper applied the Transformer model combined with the back-translation strategy module to the machine translation of English literary works. Simulation experiments compared the improved model traditional long short-term memory (LSTM) and Transformer models. The results showed that the improved model had a Bilingual Evaluation Understudy (BLEU) score of 49.9%, a Metric for Evaluation of Translation with Explicit ORdering (METEOR) score of 61.3%, a fluency score of 3.9, a translation accuracy score of 4.2, and a literary score of 4.6, respectively. These findings indicate that the proposed model translates English literary texts more accurately and aligns the translation more closely with Chinese literary style.