SimulEval: An Evaluation Toolkit for Simultaneous Translation
This provides a standardized evaluation tool for researchers working on simultaneous translation, addressing a gap in the field, though it is incremental as it focuses on evaluation rather than new modeling.
The authors tackled the lack of a universal evaluation procedure for simultaneous translation models by developing SimulEval, a toolkit that automatically evaluates both text and speech translation with latency metrics, and it has been used in the IWSLT 2020 shared task.
Simultaneous translation on both text and speech focuses on a real-time and low-latency scenario where the model starts translating before reading the complete source input. Evaluating simultaneous translation models is more complex than offline models because the latency is another factor to consider in addition to translation quality. The research community, despite its growing focus on novel modeling approaches to simultaneous translation, currently lacks a universal evaluation procedure. Therefore, we present SimulEval, an easy-to-use and general evaluation toolkit for both simultaneous text and speech translation. A server-client scheme is introduced to create a simultaneous translation scenario, where the server sends source input and receives predictions for evaluation and the client executes customized policies. Given a policy, it automatically performs simultaneous decoding and collectively reports several popular latency metrics. We also adapt latency metrics from text simultaneous translation to the speech task. Additionally, SimulEval is equipped with a visualization interface to provide better understanding of the simultaneous decoding process of a system. SimulEval has already been extensively used for the IWSLT 2020 shared task on simultaneous speech translation. Code will be released upon publication.