Synthesizer (Random + Vanilla)

Reported on 2 benchmarks across 1 task · 1 paper

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· 2020-05-02
28.47
best: 35.14 (Transformer Cycle (Rev))
Synthesizer: Rethinking Self-Attention in Transformer Models arXiv:2005.00743
Machine TranslationonWMT2014 English-French
BLEU score· 2020-05-02
41.85
best: 46.4 (Transformer+BT (ADMIN init))
Synthesizer: Rethinking Self-Attention in Transformer Models arXiv:2005.00743