SOLOIST

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
MultiWOZ (Inform)· 2020-05-11
85.5
best: 94.4 (GALAXY)
SOTA
SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching arXiv:2005.05298
DialogueonMULTIWOZ 2.0
MultiWOZ (Success)· 2020-05-11
72.9
best: 85.3 (GALAXY)
SOTA
SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching arXiv:2005.05298
DialogueonMULTIWOZ 2.0
BLEU· 2020-05-11
16.5
best: 20.6 (Noisy Channel Model)
SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching arXiv:2005.05298