论文标题
子词对齐仍然很有用：一种用于增强低资源机器翻译的背心口袋方法
Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation
论文作者
论文摘要
我们利用对齐子词之间的重复嵌入重复，以扩展亲子转移学习方法，以改善低资源机器的翻译。我们在my-en，id-en和tr-en翻译方案的基准数据集上进行实验。测试结果表明，我们的方法可产生实质性改进，分别达到22.5、28.0和18.1的BLEU得分。此外，该方法在计算上是有效的，可以将训练时间的消耗降低63.8％，在Tesla 16GB 16GB P100 GPU上训练时，训练时间达到1.6小时。实验中的所有模型和源代码都将公开使用以支持可重复的研究。
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.
