Improving Khmer-Vietnamese Machine Translation with Data Augmentation methods

Low-Resource Neural Machine Translation Improvement Using Data Augmentation Strategies

“…The results shown in Table 5 indicated that our best model achieved best results for translating from the Khmer language to the Vietnamese one. In addition, our current approach had a better performance than our previous model [18] with 0.86% BLEU score higher. [18] 54.51 Our best model 55.…”

“…In addition, our current approach had a better performance than our previous model [18] with 0.86% BLEU score higher. [18] 54.51 Our best model 55. 37 7…”

“…However, in this research, we evaluate our approach by implementing it with the lowresource Khmer-Vietnamese (Km-Vi) language pair, using a dataset with 142,000 parallel sentence pairs from Nguyen et al [16]. As far as we know, there is only two works dealing with the Km-Vi machine translation ( [17], [18]). Nguyen et al [17] presented an open-source MT toolkit for low-resource language pairs.…”

“…However, this approach only used a transformer architecture to train the original dataset, without applying fine-tuning, transfer learning, or additional data augmentation techniques. Pham and Le [18] fine-tuned mBART and applied some data augmentation strategies. In this research, we have extended the work in [18] to improve the performance of the Km-Vi NMT system.…”

“…Pham and Le [18] fine-tuned mBART and applied some data augmentation strategies. In this research, we have extended the work in [18] to improve the performance of the Km-Vi NMT system. The contributions are as follows:…”