English

From Simultaneous to Streaming Machine Translation by Leveraging Streaming History

Computation and Language 2022-04-01 v3

Abstract

Simultaneous Machine Translation is the task of incrementally translating an input sentence before it is fully available. Currently, simultaneous translation is carried out by translating each sentence independently of the previously translated text. More generally, Streaming MT can be understood as an extension of Simultaneous MT to the incremental translation of a continuous input text stream. In this work, a state-of-the-art simultaneous sentence-level MT system is extended to the streaming setup by leveraging the streaming history. Extensive empirical results are reported on IWSLT Translation Tasks, showing that leveraging the streaming history leads to significant quality gains. In particular, the proposed system proves to compare favorably to the best performing systems.

Keywords

Cite

@article{arxiv.2203.02459,
  title  = {From Simultaneous to Streaming Machine Translation by Leveraging Streaming History},
  author = {Javier Iranzo-Sánchez and Jorge Civera and Alfons Juan},
  journal= {arXiv preprint arXiv:2203.02459},
  year   = {2022}
}

Comments

ACL 2022 - Camera ready; v3: expanded data pre-processing

R2 v1 2026-06-24T10:02:30.403Z