Behind the scenes in an interactive speech translation system

Mark Seligman, Mike Dillinger


Abstract
This paper describes the facilities of Converser for Healthcare 4.0, a highly interactive speech translation system which enables users to verify and correct speech recognition and machine translation. Corrections are presently useful for real-time reliability, and in the future should prove applicable to offline machine learning. We provide examples of interactive tools in action, emphasizing semantically controlled back-translation and lexical disambiguation, and explain for the first time the techniques employed in the tools’ creation, focusing upon compilation of a database of semantic cues and its connection to third-party MT engines. Planned extensions of our techniques to statistical MT are also discussed.
Anthology ID:
2014.amta-workshop.5
Volume:
Workshop on interactive and adaptive machine translation
Month:
October 22
Year:
2014
Address:
Vancouver, Canada
Editors:
Francisco Casacuberta, Marcello Federico, Philipp Koehn
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
42–50
Language:
URL:
https://aclanthology.org/2014.amta-workshop.5
DOI:
Bibkey:
Cite (ACL):
Mark Seligman and Mike Dillinger. 2014. Behind the scenes in an interactive speech translation system. In Workshop on interactive and adaptive machine translation, pages 42–50, Vancouver, Canada. Association for Machine Translation in the Americas.
Cite (Informal):
Behind the scenes in an interactive speech translation system (Seligman & Dillinger, AMTA 2014)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2014.amta-workshop.5.pdf