ConvS2S

Reported on 4 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 Processing4 results

Machine TranslationonIWSLT2015 German-English
BLEU score· 2017-05-08
32.31
best: 36.2 (PS-KD)
SOTA
Convolutional Sequence to Sequence Learning arXiv:1705.03122
Machine TranslationonIWSLT2015 English-German
BLEU score· 2017-05-08
26.73
best: 30 (PS-KD)
SOTA
Convolutional Sequence to Sequence Learning arXiv:1705.03122
Machine TranslationonWMT2014 English-German
BLEU score· 2017-05-08
25.16
best: 35.14 (Transformer Cycle (Rev))
Convolutional Sequence to Sequence Learning arXiv:1705.03122
Machine TranslationonWMT2014 English-French
BLEU score· 2017-05-08
40.46
best: 46.4 (Transformer+BT (ADMIN init))
Convolutional Sequence to Sequence Learning arXiv:1705.03122