LIUM machine translation systems for WMT17 news translation task
File(s)1707.04499v1.pdf (249.15 KB)
Working paper
Author(s)
Type
Working Paper
Abstract
This paper describes LIUM submissions to WMT17 News Translation Task for
English-German, English-Turkish, English-Czech and English-Latvian language
pairs. We train BPE-based attentive Neural Machine Translation systems with and
without factored outputs using the open source nmtpy framework. Competitive
scores were obtained by ensembling various systems and exploiting the
availability of target monolingual corpora for back-translation. The impact of
back-translation quantity and quality is also analyzed for English-Turkish
where our post-deadline submission surpassed the best entry by +1.6 BLEU.
English-German, English-Turkish, English-Czech and English-Latvian language
pairs. We train BPE-based attentive Neural Machine Translation systems with and
without factored outputs using the open source nmtpy framework. Competitive
scores were obtained by ensembling various systems and exploiting the
availability of target monolingual corpora for back-translation. The impact of
back-translation quantity and quality is also analyzed for English-Turkish
where our post-deadline submission surpassed the best entry by +1.6 BLEU.
Date Issued
2017-07-14
Citation
2017
Publisher
arxiv
Copyright Statement
© 2017 The Authors.
Identifier
http://arxiv.org/abs/1707.04499v1
Subjects
cs.CL
cs.CL
Notes
News Translation Task System Description paper for WMT17
Publication Status
Published