论文标题
双重重建：半监督神经机器翻译的统一目标
Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation
论文作者
论文摘要
虽然迭代的反向翻译和双重学习有效地将单语培训数据纳入了神经机器的翻译中，但他们使用了不同的目标和启发式梯度近似策略，并且尚未得到广泛的比较。我们介绍了一个新颖的双重重建目标，该目标提供了迭代反向翻译和双重学习的统一观点。它激发了对德语 - 英语和土耳其 - 英语任务的理论分析和控制经验研究，这两者都表明迭代反向翻译比双重学习相对简单，更有效。
While Iterative Back-Translation and Dual Learning effectively incorporate monolingual training data in neural machine translation, they use different objectives and heuristic gradient approximation strategies, and have not been extensively compared. We introduce a novel dual reconstruction objective that provides a unified view of Iterative Back-Translation and Dual Learning. It motivates a theoretical analysis and controlled empirical study on German-English and Turkish-English tasks, which both suggest that Iterative Back-Translation is more effective than Dual Learning despite its relative simplicity.
