Automated Scoring of Translations with BERT Models: Chinese and English Language Case Study

Abstract

With the wide application of artificial intelligence represented by deep learning in natural language-processing tasks, the automated scoring of translations has also advanced and improved. This study aims to determine if the BERT-assist system can reliably assess translation quality and identify high-quality translations for potential recognition. It takes the Han Suyin International Translation Contest as a case study, which is a large-scale and influential translation contest in China, with a history of over 30 years. The experimental results show that the BERT-assist system is a reliable second rater for massive translations in terms of translation quality, as it can effectively sift out high-quality translations with a reliability of r = 0.9 or higher. Thus, the automated translation scoring system based on BERT can satisfactorily predict the ranking of translations according to translation quality and sift out high-quality translations potentially shortlisted for prizes.