VBD-MT Chinese-Vietnamese Translation Systems for VLSP 2022

TL;DR

This paper describes neural Transformer-based Chinese-Vietnamese translation systems using mBART and backtranslation, achieving high BLEU scores in the VLSP 2022 shared task.

Contribution

It introduces a multilingual denoising pre-trained model with backtranslation sampling and ensemble techniques for improved translation quality.

Findings

Achieved 38.9 BLEU on Chinese-Vietnamese translation.

Achieved 38.0 BLEU on Vietnamese-Chinese translation.

Outperformed several strong baselines.

Abstract

We present our systems participated in the VLSP 2022 machine translation shared task. In the shared task this year, we participated in both translation tasks, i.e., Chinese-Vietnamese and Vietnamese-Chinese translations. We build our systems based on the neural-based Transformer model with the powerful multilingual denoising pre-trained model mBART. The systems are enhanced by a sampling method for backtranslation, which leverage large scale available monolingual data. Additionally, several other methods are applied to improve the translation quality including ensembling and postprocessing. We achieve 38.9 BLEU on ChineseVietnamese and 38.0 BLEU on VietnameseChinese on the public test sets, which outperform several strong baselines.