THPN

Reported on 4 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech2 results

DialogueonKVRET
BLEU
12.8
best: 17.35 (TTOS)
DialogueonKVRET
Entity F1
37.8
best: 70.07 (T5-3b(UnifiedSKG))

Natural Language Processing2 results

Task-Oriented Dialogue SystemsonKVRET
BLEU
12.8
best: 17.35 (TTOS)
Task-Oriented Dialogue SystemsonKVRET
Entity F1
37.8
best: 70.07 (T5-3b(UnifiedSKG))