ConvS2S (ensemble)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Machine TranslationonWMT2014 English-German
BLEU score· 2017-05-08
26.4
best: 35.14 (Transformer Cycle (Rev))
SOTA
Convolutional Sequence to Sequence Learning arXiv:1705.03122
Machine TranslationonWMT2014 English-French
BLEU score· 2017-05-08
41.3
best: 46.4 (Transformer+BT (ADMIN init))
SOTA
Convolutional Sequence to Sequence Learning arXiv:1705.03122