Stream-level Latency Evaluation for Simultaneous Machine Translation

Javier Iranzo-Sánchez, Jorge Civera Saiz, Alfons Juan


Abstract
Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between translation quality and response time, and with this purpose multiple latency measures have been proposed. However, latency evaluations for simultaneous translation are estimated at the sentence level, not taking into account the sequential nature of a streaming scenario. Indeed, these sentence-level latency measures are not well suited for continuous stream translation, resulting in figures that are not coherent with the simultaneous translation policy of the system being assessed. This work proposes a stream level adaptation of the current latency measures based on a re-segmentation approach applied to the output translation, that is successfully evaluated on streaming conditions for a reference IWSLT task.
Anthology ID:
2021.findings-emnlp.58
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
664–670
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.58
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.58.pdf
Code
 jairsan/Stream-level_Latency_Evaluation_for_Simultaneous_Machine_Translation