Simultaneous machine translation (SiMT) starts to output translation while reading the source sentence and needs a precise policy to decide when to output the generated translation. Therefore, the policy determines the number of source tokens read during the translation of each target token. However, it is difficult to learn a precise translation policy to achieve good latency-quality trade-offs, because there is no golden policy corresponding to parallel sentences as explicit supervision. In this paper, we present a new method for constructing the optimal policy online via binary search. By employing explicit supervision, our approach enables the SiMT model to learn the optimal policy, which can guide the model in completing the translation during inference. Experiments on four translation tasks show that our method can exceed strong baselines across all latency scenarios.

翻译：同步机器翻译（SiMT）在读取源句子的同时开始输出译文，需要精确的策略来决定何时输出生成的译文。因此，该策略决定了翻译每个目标词时所读取的源词数量。然而，由于不存在与平行句子对应的黄金策略作为显式监督，学习精确的翻译策略以实现良好的延迟-质量权衡十分困难。本文提出了一种通过二分搜索在线构建最优策略的新方法。通过引入显式监督，我们的方法使SiMT模型能够学习最优策略，从而在推理过程中指导模型完成翻译。在四项翻译任务上的实验表明，我们的方法在所有延迟场景下均能超越强基线模型。