FLOATER-large

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing3 results

Machine TranslationonWMT2014 English-German
BLEU score· 2020-03-13
29.2
best: 35.14 (Transformer Cycle (Rev))
Learning to Encode Position for Transformer with Continuous Dynamical Model arXiv:2003.09229
Machine TranslationonWMT2014 English-French
BLEU score· 2020-03-13
42.7
best: 46.4 (Transformer+BT (ADMIN init))
Learning to Encode Position for Transformer with Continuous Dynamical Model arXiv:2003.09229
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2020-03-13
96.7
best: 97.5 (T5-11B)
Learning to Encode Position for Transformer with Continuous Dynamical Model arXiv:2003.09229