Noisy Channel Model

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.

Speech3 results

DialogueonMULTIWOZ 2.0
BLEU· 2021-03-18
20.6
SOTA
Pretraining the Noisy Channel Model for Task-Oriented Dialogue arXiv:2103.10518
DialogueonMULTIWOZ 2.0
MultiWOZ (Success)· 2021-03-18
76.2
best: 85.3 (GALAXY)
SOTA
Pretraining the Noisy Channel Model for Task-Oriented Dialogue arXiv:2103.10518
DialogueonMULTIWOZ 2.0
MultiWOZ (Inform)· 2021-03-18
86.9
best: 94.4 (GALAXY)
Pretraining the Noisy Channel Model for Task-Oriented Dialogue arXiv:2103.10518