Type

Conference Proceedings

Authors

Andy Way
Gideon Maillette de Buy Wenniger
Alberto Poncelas

Subjects

Linguistics

Topics
training feature selection german machine translation english neural machine translation statistical machine translation feature decay algorithms

Feature decay algorithms for neural machine translation (2018)

Abstract Neural Machine Translation (NMT) systems require a lot of data to be competitive. For this reason, data selection techniques are used only for finetuning systems that have been trained with larger amounts of data. In this work we aim to use Feature Decay Algorithms (FDA) data selection techniques not only to fine-tune a system but also to build a complete system with less data. Our findings reveal that it is possible to find a subset of sentence pairs, that outperforms by 1.11 BLEU points the full training corpus, when used for training a German-English NMT system .
Collections Ireland -> Dublin City University -> Publication Type = Conference or Workshop Item
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing: School of Computing
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres: ADAPT
Ireland -> Dublin City University -> Status = Published

Full list of authors on original publication

Andy Way, Gideon Maillette de Buy Wenniger, Alberto Poncelas

Experts in our system

1
Andy Way
Dublin City University
Total Publications: 229
 
2
Gideon Maillette de Buy Wenniger
Dublin City University
Total Publications: 6
 
3
Alberto Poncelas
Dublin City University
Total Publications: 8