Kg To Text Generation On Webnlg 2 0 1
評価指標
BLEU
METEOR
ROUGE
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | BLEU | METEOR | ROUGE | Paper Title | Repository |
|---|---|---|---|---|---|
| JointGT (BART) | 58.55 | 45.01 | 72.31 | JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs | |
| JointGT (T5) | 61.01 | 46.32 | 73.57 | JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs | |
| SOTA-NPT | 48.0 | 36.0 | 65.0 | Handling Rare Items in Data-to-Text Generation | |
| BART | 56.65 | 44.51 | 70.94 | JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs | |
| T5 | 58.66 | 46.04 | 73.06 | JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs |
0 of 5 row(s) selected.