BiBERT
Reported on 3 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 Processing3 results
- BLEU score· 2021-09-09SOTA38.61best: 40.43 (PiNMT)
- BLEU score· 2021-09-09SOTA34.94best: 35.15 (Bi-SimCut)
- BLEU score· 2021-09-0931.26best: 35.14 (Transformer Cycle (Rev))