Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing the source-side context. However, there is a counterintuitive phenomenon about the context usage between training and testing: e.g., the wait-k testing model consistently trained with wait-k is much worse than that model inconsistently trained with wait-k' (k' is not equal to k) in terms of translation quality. To this end, we first investigate the underlying reasons behind this phenomenon and uncover the following two factors: 1) the limited correlation between translation quality and training (cross-entropy) loss; 2) exposure bias between training and testing. Based on both reasons, we then propose an effective training approach called context consistency training accordingly, which makes consistent the context usage between training and testing by optimizing translation quality and latency as bi-objectives and exposing the predictions to the model during the training. The experiments on three language pairs demonstrate our intuition: our system encouraging context consistency outperforms that existing systems with context inconsistency for the first time, with the help of our context consistency training approach.

翻译：同步机器翻译（SiMT）旨在通过单调递增的源端上下文生成实时部分翻译。然而，训练与测试中的上下文使用存在一个反直觉现象：例如，使用wait-k训练的测试模型在翻译质量上远差于使用wait-k'（k'≠k）不一致训练的模型。为此，我们首先探究了这一现象背后的原因，并发现以下两个因素：1）翻译质量与训练（交叉熵）损失之间的有限相关性；2）训练与测试之间的暴露偏差。基于这两个原因，我们随后提出了一种有效的训练方法，即上下文一致性训练，该方法通过将翻译质量和延迟作为双目标进行优化，并在训练期间将预测结果暴露给模型，从而使得训练与测试中的上下文使用保持一致。在三个语言对上的实验验证了我们的直觉：借助上下文一致性训练方法，我们的系统首次在鼓励上下文一致性方面优于现有上下文不一致的系统。