InDeep × NMT: Empowering Human Translators via Interpretable Neural Machine Translation

OnderzoeksoutputAcademicpeer review

4 Downloads (Pure)

Samenvatting

Neural machine translation (NMT) systems are nowadays essential components of professional translation workflows. Consequently, human translators are increasingly working as post-editors for machine-translated content. The NWO-funded InDeep project aims to empower users of Deep Learning models of text, speech, and music by improving their ability to interact with such models and interpret their behaviors. In the specific context of translation, we aim at developing new tools and methodologies to improve prediction attribution, error analysis, and controllable generation for NMT systems. These advances will be evaluated through field studies involving professional translators to assess gains in efficiency and overall enjoyability of the post-editing process.
Originele taal-2English
TitelProceedings of the 23rd Annual Conference of the European Association for Machine Translation
RedacteurenHelena Moniz, Lieve Macken, Andrew Rufener, Loïc Barrault, Marta R. Costa-jussà, Christophe Declercq, Maarit Koponen, Ellie Kemp, Spyridon Pilos, Mikel L. Forcada, Carolina Scarton, Joachim van den Bogaert, Joke Daems, Arda Tezcan, Bram Vanroy, Margot Fonteyne
UitgeverijEuropean Association for Machine Translation
Pagina's313-314
Aantal pagina's2
StatusPublished - jun.-2022
Evenement23rd Annual Conference of the European Association for Machine Translation - Zebrastraat, Ghent, Belgium
Duur: 1-jun.-20223-jun.-2022
https://eamt2022.com/

Conference

Conference23rd Annual Conference of the European Association for Machine Translation
Verkorte titelEAMT '22
Land/RegioBelgium
StadGhent
Periode01/06/202203/06/2022
Internet adres

Citeer dit