NQG++
Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing1 result
- BLEU-4· 2017-04-06SOTA13.27best: 25.41 (ERNIE-GENLARGE (beam size=5))