DREAM+Unicoder-VL (MSRA)
Reported on 7 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing7 results
- 76.04best: 89.3 (human)
- 84.46best: 91.2 (human)
- Consistency91.47best: 98.4 (human)
- Distribution3.68best: 93.08 (GlobalPrior)
- 68.6best: 87.4 (human)
- Plausibility83.75best: 97.2 (human)
- 96.42best: 98.9 (human)