Large amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. In this case, the way of using data appears to be more important. Here, we investigate the effective use of training data for low-resource NMT. In particular, we propose a dynamic curriculum learning (DCL) method to reorder training samples in training. Unlike previous work, we do not use a static scoring function for reordering. Instead, the order of training samples is dynamically determined in two ways - loss decline and model competence. This eases training by highlighting easy samples that the current model has enough competence to learn. We test our DCL method in a Transformer-based system. Experimental results show that DCL outperforms several strong baselines on three low-resource machine translation benchmarks and different sized data of WMT' 16 En-De.
翻译:大量数据使神经机器翻译(NMT)近年来取得了巨大成功。 但是,如果我们在小型公司上培训这些模型,这仍然是一个挑战。 在这种情况下,使用数据的方式似乎更为重要。在这里,我们调查了低资源NMT培训数据的有效使用情况。特别是,我们建议采用动态课程学习(DCL)方法来重新订购培训样本。与以往的工作不同,我们不使用静态评分功能来重新排序。相反,培训样本的顺序是以两种方式动态决定的:损失下降和模型能力。这通过突出当前模型具有足够学习能力的简单样本来便利培训。我们在以变换器为基础的系统中测试DCL方法。实验结果表明,DCL在三个低资源机器翻译基准和WMT' 16 E-De不同大小的数据上比几个强的基线要强。