English

Presenting Simultaneous Translation in Limited Space

Computation and Language 2020-09-22 v1

Abstract

Some methods of automatic simultaneous translation of a long-form speech allow revisions of outputs, trading accuracy for low latency. Deploying these systems for users faces the problem of presenting subtitles in a limited space, such as two lines on a television screen. The subtitles must be shown promptly, incrementally, and with adequate time for reading. We provide an algorithm for subtitling. Furthermore, we propose a way how to estimate the overall usability of the combination of automatic translation and subtitling by measuring the quality, latency, and stability on a test set, and propose an improved measure for translation latency.

Keywords

Cite

@article{arxiv.2009.09016,
  title  = {Presenting Simultaneous Translation in Limited Space},
  author = {Dominik Macháček and Ondřej Bojar},
  journal= {arXiv preprint arXiv:2009.09016},
  year   = {2020}
}
R2 v1 2026-06-23T18:39:03.810Z