Average Token Delay: A Latency Metric for Simultaneous Translation
This work addresses the need for better latency metrics in simultaneous translation to improve user comprehension, though it is incremental as it builds on prior metrics.
The paper tackled the problem of evaluating latency in simultaneous translation by proposing Average Token Delay (ATD), a metric that focuses on when translation ends rather than starts, and demonstrated its advantages through simulated examples and experiments comparing it to existing metrics like Average Lagging.
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.