< Terug naar vorige pagina

Publicatie

Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation

Boekbijdrage - Boekhoofdstuk Conferentiebijdrage

We present a simple yet powerful data augmentation method for boosting Neural Machine Translation (NMT) performance by leveraging information retrieved from a Translation Memory (TM). We propose and test two methods for augmenting NMT training data with fuzzy TM matches. Tests on the DGT-TM data set for two language pairs show consistent and substantial improvements over a range of baseline systems. The results suggest that this method is promising for any translation environment in which a sizeable TM is available and a certain amount of repetition across translations is to be expected, especially considering its ease of implementation.
Boek: Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL)
Pagina's: 1800 - 1809
Aantal pagina's: 10
ISBN:978-1-950737-48-2
Jaar van publicatie:2019
BOF-keylabel:ja
IOF-keylabel:ja
Authors from:Higher Education