Neural Interactive Translation Prediction

Rebecca Knowles, Philipp Koehn


Abstract
We present an interactive translation prediction method based on neural machine translation. Even with the same translation quality of the underlying machine translation systems, the neural prediction method yields much higher word prediction accuracy (61.6% vs. 43.3%) than the traditional method based on search graphs, mainly due to better recovery from errors. We also develop efficient means to enable practical deployment.
Anthology ID:
2016.amta-researchers.9
Volume:
Conferences of the Association for Machine Translation in the Americas: MT Researchers' Track
Month:
October 28 - November 1
Year:
2016
Address:
Austin, TX, USA
Editors:
Spence Green, Lane Schwartz
Venue:
AMTA
SIG:
Publisher:
The Association for Machine Translation in the Americas
Note:
Pages:
107–120
Language:
URL:
https://aclanthology.org/2016.amta-researchers.9
DOI:
Bibkey:
Cite (ACL):
Rebecca Knowles and Philipp Koehn. 2016. Neural Interactive Translation Prediction. In Conferences of the Association for Machine Translation in the Americas: MT Researchers' Track, pages 107–120, Austin, TX, USA. The Association for Machine Translation in the Americas.
Cite (Informal):
Neural Interactive Translation Prediction (Knowles & Koehn, AMTA 2016)
Copy Citation:
PDF:
https://aclanthology.org/2016.amta-researchers.9.pdf