Neural Interactive Translation Prediction

Rebecca Knowles, Philipp Koehn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.
Original languageEnglish
Title of host publicationProceedings of AMTA 2016, vol. 1: MT Researchers’ Track
Place of PublicationAustin, Texas, USA
PublisherAssociation for Machine Translation in the Americas, AMTA
Pages107-120
Number of pages14
Publication statusPublished - 1 Nov 2016
EventTwelfth Conference of The Association for Machine Translation in the Americas - Austin, United States
Duration: 28 Oct 20161 Nov 2016
http://www.amta2016.org/
https://amtaweb.org/amta-2016-proceedings-are-available/

Conference

ConferenceTwelfth Conference of The Association for Machine Translation in the Americas
Abbreviated titleAMTA 2016
Country/TerritoryUnited States
CityAustin
Period28/10/161/11/16
Internet address

Fingerprint

Dive into the research topics of 'Neural Interactive Translation Prediction'. Together they form a unique fingerprint.

Cite this