Simultaneous machine translation (SiMT) outputs translation while reading the source sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT methods adopt the prefix-to-prefix (prefix2prefix) training, where the model predicts target tokens based on partial source tokens. However, the prefix2prefix training diminishes the ability of the model to capture global information and introduces forced predictions due to the absence of essential source information. Consequently, it is crucial to bridge the gap between the prefix2prefix training and seq2seq training to enhance the translation capability of the SiMT model. In this paper, we propose a novel method that glances future in curriculum learning to achieve the transition from the seq2seq training to prefix2prefix training. Specifically, we gradually reduce the available source information from the whole sentence to the prefix corresponding to that latency. Our method is applicable to a wide range of SiMT methods and experiments demonstrate that our method outperforms strong baselines.

翻译：同时机器翻译（SiMT）在读取源句子的同时输出译文。与传统的序列到序列（seq2seq）训练不同，现有SiMT方法采用前缀到前缀（prefix2prefix）训练，即基于部分源词预测目标词。然而，prefix2prefix训练削弱了模型捕捉全局信息的能力，并因缺乏关键源信息而引入强制预测。因此，弥合prefix2prefix训练与seq2seq训练之间的差距以增强SiMT模型的翻译能力至关重要。本文提出一种基于课程学习的前瞻未来方法，实现从seq2seq训练到prefix2prefix训练的过渡。具体而言，我们逐步减少可用的源信息，从完整句子缩减至对应于该延迟的前缀。该方法适用于多种SiMT方法，实验结果表明其性能优于强基线模型。