Data To Text Generation On Multiwoz 2 1

BLEU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
T5-Base	35.1	Text-to-Text Pre-Training for Data-to-Text Tasks
T5-small	34.96	Template Guided Text Generation for Task-Oriented Dialogue
T2G2	34.91	Template Guided Text Generation for Task-Oriented Dialogue
SC-GPT2	30.76	Few-shot Natural Language Generation for Task-Oriented Dialog
HDSA	26.48	Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention

0 of 5 row(s) selected.