Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation
This is an incremental improvement for low-resource machine translation, enhancing efficiency and performance in specific language pairs.
The paper tackles low-resource machine translation by extending Parent-Child transfer learning with sub-word alignment, achieving BLEU scores of 22.5, 28.0, and 18.1 on My-En, Id-En, and Tr-En benchmarks, and reducing training time by 63.8% to 1.6 hours.
We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En translation scenarios. The test results show that our method produces substantial improvements, achieving the BLEU scores of 22.5, 28.0 and 18.1 respectively. In addition, the method is computationally efficient which reduces the consumption of training time by 63.8%, reaching the duration of 1.6 hours when training on a Tesla 16GB P100 GPU. All the models and source codes in the experiments will be made publicly available to support reproducible research.