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.

机器同时翻译（SiMT）旨在实时产生一个具有单调增长源侧上下文的部分翻译。然而，存在一个关于训练和测试之间上下文使用的反直觉现象：例如，以 wait-k 一致训练的 wait-k 测试模型在翻译质量方面明显劣于以 wait-k'（k' 不等于 k）一致训练的模型。为此，我们首先调查了这一现象背后的原因，并发现了以下两个因素：1）翻译质量与训练（交叉熵）损失之间的有限相关性；2）训练和测试之间的曝光偏差。基于这两个原因，我们提出了一种有效的培训方法，称为上下文一致性训练，通过优化翻译质量和延迟作为双目标，并在训练过程中向模型暴露预测结果，使训练和测试之间的上下文使用保持一致。三种语言对的实验证明了我们的直觉：我们鼓励上下文一致性的系统首次在上下文不一致性的现有系统之上取得了更好的性能，借助于我们的上下文一致性训练方法。