LIUM Machine Translation Systems for WMT17 News Translation Task
This work addresses machine translation for multiple language pairs, but it is incremental as it builds on existing methods like BPE and back-translation.
The authors tackled the WMT17 News Translation Task by training BPE-based attentive Neural Machine Translation systems with factored outputs and ensembling, achieving competitive scores and surpassing the best entry by +1.6 BLEU for English-Turkish through back-translation analysis.
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.