Average Token Delay: A Latency Metric for Simultaneous Translation

TL;DR

This paper introduces Average Token Delay, a new latency metric for simultaneous translation that emphasizes the end timing of translations, addressing limitations of existing metrics that overlook translation length delays.

Contribution

The paper proposes the novel Average Token Delay metric, which better captures translation latency by considering when the translation ends, improving evaluation of simultaneous translation systems.

Findings

ATD effectively captures end-of-translation delays.

ATD differs from Average Lagging in evaluation.

Simulated and experimental analyses validate ATD's advantages.

Abstract

Simultaneous translation is a task in which translation begins before the speaker has finished speaking. In its evaluation, we have to consider the latency of the translation in addition to the quality. The latency is preferably as small as possible for users to comprehend what the speaker says with a small delay. Existing latency metrics focus on when the translation starts but do not consider adequately when the translation ends. This means such metrics do not penalize the latency caused by a long translation output, which actually delays users' comprehension. In this work, we propose a novel latency evaluation metric called Average Token Delay (ATD) that focuses on the end timings of partial translations in simultaneous translation. We discuss the advantage of ATD using simulated examples and also investigate the differences between ATD and Average Lagging with simultaneous translation experiments.