Abstract

Abstract Under the background of big data development, more intelligent technologies make work and life convenient, and the traditional English-US literature translation methods and means are difficult to adapt to the fast-paced era of big data, so this paper conducts research and analysis on this problem. In terms of the English-Chinese translation strategy based on BERT and multi-similarity fusion of English and American literature, the article first introduces the concept and principle of BERT, and multi-similarity fusion algorithm then constructs the model of BERT and multi-similarity algorithm fusion, analyzes and discusses the English and American literature translation dataset respectively, and compares it with three different similarity algorithms in terms of three indicators. The data shows that BERT has the greatest effect on the accuracy rate, followed by BLEU value and Manhattan distance. Compared with the fusion of the three methods, the data analysis of a single method is better, and the three selected index values all remain above 90%, and this study is conducive to improving the accuracy and efficiency of English and American literature work, which is of great historical significance for international literary communication.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call