Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation

TL;DR

This paper introduces a novel approach to simultaneous machine translation by integrating post-evaluation into the adaptive policy, enabling better decision-making and improved latency-quality tradeoffs.

Contribution

It proposes a method that evaluates the rationality of translation actions after token generation, enhancing adaptive policy effectiveness in SiMT.

Findings

Outperforms strong baselines across multiple translation tasks

Achieves better latency-quality tradeoffs

Reduces incorrect translation actions

Abstract

Simultaneous machine translation (SiMT) starts its translation before reading the whole source sentence and employs either fixed or adaptive policy to generate the target sentence. Compared to the fixed policy, the adaptive policy achieves better latency-quality tradeoffs by adopting a flexible translation policy. If the policy can evaluate rationality before taking action, the probability of incorrect actions will also decrease. However, previous methods lack evaluation of actions before taking them. In this paper, we propose a method of performing the adaptive policy via integrating post-evaluation into the fixed policy. Specifically, whenever a candidate token is generated, our model will evaluate the rationality of the next action by measuring the change in the source content. Our model will then take different actions based on the evaluation results. Experiments on three translation tasks show that our method can exceed strong baselines under all latency.