Weighted Transformer (large)
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
- BLEU score· 2017-11-06SOTA28.9best: 35.14 (Transformer Cycle (Rev))
- BLEU score· 2017-11-06SOTA41.4best: 46.4 (Transformer+BT (ADMIN init))