论文标题
低资源机器翻译中子字正规模型的单型集合
Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation
论文作者
论文摘要
子字正规化在训练过程中使用多个子词分段，以改善神经机器翻译模型的鲁棒性。在以前的子字正规化中，我们在培训过程中使用多个分段，但在推理中仅使用一个细分。在这项研究中，我们提出了一种解决这一差异的推论策略。提出的策略通过使用多个分割（包括最合理的分割和几个采样分割）来近似边缘化的可能性。由于提出的策略汇总了几个细分的预测，因此我们可以将其视为单个模型集合，不需要任何额外的培训费用。实验结果表明，所提出的策略改善了在低资源机器翻译任务中用子字正则化训练的模型的性能。
Subword regularizations use multiple subword segmentations during training to improve the robustness of neural machine translation models. In previous subword regularizations, we use multiple segmentations in the training process but use only one segmentation in the inference. In this study, we propose an inference strategy to address this discrepancy. The proposed strategy approximates the marginalized likelihood by using multiple segmentations including the most plausible segmentation and several sampled segmentations. Because the proposed strategy aggregates predictions from several segmentations, we can regard it as a single model ensemble that does not require any additional cost for training. Experimental results show that the proposed strategy improves the performance of models trained with subword regularization in low-resource machine translation tasks.
