Year: 2017
Type: conference-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.
DOI: 10.18653/v1/w17-4726
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2735139879
