论文标题
数据驱动的自适应同时机器翻译
Data-Driven Adaptive Simultaneous Machine Translation
论文作者
论文摘要
在同时翻译（SIMULMT）中，最广泛使用的策略是Wait-K策略，这要归功于其在平衡翻译质量和潜伏期方面的简单性和有效性。但是，WAIT-K受到了两个主要局限性：（a）这是一个固定的策略，无法自适应地调整潜伏期的情况，并且（b）其培训比全句子翻译要慢得多。为了减轻这些问题，我们通过使用自适应前缀到排名对增强训练语料库来提出一种新颖有效的培训计划，以进行自适应SimulMT，而培训的复杂性与培训全句子翻译模型的复杂性保持不变。两种语言对的实验表明，在翻译质量和延迟方面，我们的方法优于所有强大的基线。
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, wait-k suffers from two major limitations: (a) it is a fixed policy that can not adaptively adjust latency given context, and (b) its training is much slower than full-sentence translation. To alleviate these issues, we propose a novel and efficient training scheme for adaptive SimulMT by augmenting the training corpus with adaptive prefix-to-prefix pairs, while the training complexity remains the same as that of training full-sentence translation models. Experiments on two language pairs show that our method outperforms all strong baselines in terms of translation quality and latency.
