An Efficient Approach for Machine Translation on Low-resource Languages: A Case Study in Vietnamese-Chinese

TL;DR

This paper presents a novel method for machine translation in low-resource languages, combining multilingual pre-trained models and monolingual data to improve translation quality, demonstrated on Vietnamese-Chinese translation.

Contribution

It introduces a new approach that leverages monolingual corpora and pre-trained models to enhance low-resource language translation performance.

Findings

Outperformed standard transformer models by 8%.

Augmented training data improved translation accuracy.

Effective sentence selection from monolingual data.

Abstract

Despite the rise of recent neural networks in machine translation, those networks do not work well if the training data is insufficient. In this paper, we proposed an approach for machine translation in low-resource languages such as Vietnamese-Chinese. Our proposed method leveraged the power of the multilingual pre-trained language model (mBART) and both Vietnamese and Chinese monolingual corpus. Firstly, we built an early bird machine translation model using the bilingual training dataset. Secondly, we used TF-IDF technique to select sentences from the monolingual corpus which are the most related to domains of the parallel dataset. Finally, the first model was used to synthesize the augmented training data from the selected monolingual corpus for the translation model. Our proposed scheme showed that it outperformed 8% compared to the transformer model. The augmented dataset also pushed the model performance.