Supervised learning in Neural Machine Translation (NMT) typically follows a teacher forcing paradigm where reference tokens constitute the conditioning context in the model's prediction, instead of its own previous predictions. In order to alleviate this lack of exploration in the space of translations, we present a simple extension of standard maximum likelihood estimation by a contrastive marking objective. The additional training signals are extracted automatically from reference translations by comparing the system hypothesis against the reference, and used for up/down-weighting correct/incorrect tokens. The proposed new training procedure requires one additional translation pass over the training set per epoch, and does not alter the standard inference setup. We show that training with contrastive markings yields improvements on top of supervised learning, and is especially useful when learning from postedits where contrastive markings indicate human error corrections to the original hypotheses. Code is publicly released.

翻译：神经机器翻译（NMT）中的监督学习通常遵循教师强制范式，即参考词元构成模型预测中的条件上下文，而非其自身的先前预测。为缓解这一在翻译空间中的探索不足，我们提出了一种标准最大似然估计的简单扩展方法，通过引入对比标记目标。额外的训练信号通过将系统假设与参考翻译进行对比，从参考翻译中自动提取，并用于对正确/错误词元进行上/下加权。所提出的新训练流程每个训练周期仅需对训练集额外进行一次翻译传递，且不改变标准推理设置。我们证明，使用对比标记进行训练能够在监督学习基础上带来改进，并且在基于后编辑学习时尤其有效，因为此时对比标记指示了原始假设中的人工纠错。代码已公开。