Projects per year
We participated in the WMT 2016 shared news translation task by building neural translation systems for four language pairs, each trained in both directions: English↔Czech, English↔German, English↔Romanian and English↔Russian. Our systems are based on an attentional encoder-decoder, using BPE subword segmentation for open-vocabulary translation with a fixed vocabulary. We experimented with using automatic back-translations of the monolingual News corpus as additional training data, pervasive dropout, and target-bidirectional models. All reported methods give substantial improvements, and we see improvements of 4.3–11.2 BLEU over our baseline systems. In the human evaluation, our systems were the (tied) best constrained system for 7 out of 8 translation directions in which we participated.
|Title of host publication||Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers|
|Place of Publication||Berlin, Germany|
|Publisher||Association for Computational Linguistics|
|Number of pages||6|
|Publication status||Published - 12 Aug 2016|
|Event||First Conference on Machine Translation - Berlin, Germany|
Duration: 11 Aug 2016 → 12 Aug 2016
|Conference||First Conference on Machine Translation|
|Period||11/08/16 → 12/08/16|
- 3 Finished
Koehn, P. & Birch-Mayne, A.
1/02/15 → 31/01/18