The primary objective of simultaneous machine translation (SiMT) is to minimize latency while preserving the quality of the final translation. Drawing inspiration from CPU branch prediction techniques, we propose incorporating branch prediction techniques in SiMT tasks to reduce translation latency. Specifically, we utilize a language model as a branch predictor to predict potential branch directions, namely, future source words. Subsequently, we utilize the predicted source words to decode the output in advance. When the actual source word deviates from the predicted source word, we use the real source word to decode the output again, replacing the predicted output. To further reduce computational costs, we share the parameters of the encoder and the branch predictor, and utilize a pre-trained language model for initialization. Our proposed method can be seamlessly integrated with any SiMT model. Extensive experimental results demonstrate that our approach can improve translation quality and latency at the same time. Our code is available at https://github.com/YinAoXiong/simt_branch_predictor .

翻译：同步机器翻译（SiMT）的主要目标是在保持最终翻译质量的同时最小化延迟。受CPU分支预测技术启发，我们提出在SiMT任务中引入分支预测技术以降低翻译延迟。具体而言，我们利用语言模型作为分支预测器，预测潜在的分支方向（即未来源语言词汇）。随后，我们利用预测的源语言词汇提前解码输出。当实际源语言词汇与预测结果不一致时，我们使用真实源语言词汇重新解码输出，替代预测输出。为进一步降低计算成本，我们共享编码器与分支预测器的参数，并利用预训练语言模型进行初始化。所提方法可无缝集成至任意SiMT模型。大量实验结果表明，我们的方法能同时提升翻译质量与延迟表现。代码已开源至 https://github.com/YinAoXiong/simt_branch_predictor 。