论文标题
理解和减轻零摄影翻译中的不确定性
Understanding and Mitigating the Uncertainty in Zero-Shot Translation
论文作者
论文摘要
零射击翻译是构建全面的多语言神经机器翻译〜（MNMT）系统的有希望的方向。但是，由于脱靶问题，其质量仍然不满意。在本文中，我们旨在从零摄影翻译中的不确定性的角度理解和减轻脱靶问题。通过仔细检查翻译输出和模型置信度，我们确定了两个不确定性，这些不确定性是脱离目标问题的原因，即外部数据不确定性和内在模型不确定性。根据观察结果，我们提出了两种轻巧和互补的方法，以将模型培训的培训数据降低，并明确地通过模型培训期间的不可能培训来惩罚脱离目标翻译。在平衡和不平衡数据集上进行的广泛实验表明，我们的方法显着提高了零光转换的性能，而不是强大的MNMT基线。
Zero-shot translation is a promising direction for building a comprehensive multilingual neural machine translation~(MNMT) system. However, its quality is still not satisfactory due to off-target issues. In this paper, we aim to understand and alleviate the off-target issues from the perspective of uncertainty in zero-shot translation. By carefully examining the translation output and model confidence, we identify two uncertainties that are responsible for the off-target issues, namely, extrinsic data uncertainty and intrinsic model uncertainty. Based on the observations, we propose two lightweight and complementary approaches to denoise the training data for model training and explicitly penalize the off-target translations by unlikelihood training during model training. Extensive experiments on both balanced and imbalanced datasets show that our approaches significantly improve the performance of zero-shot translation over strong MNMT baselines.
