Data-to-text generation on WTQ (test) benchmark leaderboard · SOTA2 Research

Data-to-text generation on WTQ (test)

62.25ROUGE-1Fully-supervised fine-tuning

Evaluation Results

Method
Fully-supervised fine-tuning2023.05	62.25	34.59	49.41	39.17	21.18	92.88	24.18
CycleNLG2023.05	61.54	34.25	49.07	39.09	20.93	92.66	24.39
CycleNLG2023.05	61.27	33.45	48.22	39.06	20.46	92.67	23.05
Low-resource fine-tuning2023.05	55.89	31.6	46.73	31.98	15.34	91.91	23.36
Low-resource fine-tuning + additional pre-training2023.05	55.57	30.48	44.47	33.73	15.89	91.53	22.88