Graph-to-text generation on WebNLG unseen (test)
54BLEUT5-large
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| T5-largeLearning Paradigm=Supervised, Training Setup=Synthetic corpus (934k samples), Approach Type=End-to-end2022.12 | 54 | 43 | |
| GPT-2-largeLearning Paradigm=Supervised, Training Setup=Synthetic corpus (934k samples), Approach Type=End-to-end2022.12 | 43.1 | 38 | |
| MURMURLearning Paradigm=Few-shot, Number of demonstrations (k)=12022.12 | 41.1 | 37.1 | |
| Direct PromptingLearning Paradigm=Few-shot, Number of demonstrations (k)=52022.12 | 38.9 | 34.3 | |
| Direct PromptingLearning Paradigm=Few-shot, Number of demonstrations (k)=12022.12 | 34.2 | 31.2 | |
| MELBOURNELearning Paradigm=Supervised, Training Setup=7k in-domain samples, Approach Type=End-to-end2022.12 | 33.2 | 33 | |
| CoT PromptingLearning Paradigm=Few-shot, Number of demonstrations (k)=12022.12 | 14.9 | 22.9 |