Kg To Text Generation On Eventnarrative
評価指標
BLEU
BertScore
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
比較表
| モデル名 | BLEU | BertScore | METEOR | ROUGE |
|---|---|---|---|---|
| gap-a-graph-aware-language-model-framework | 35.08 | 93.38 | 27.5 | 64.28 |
| gap-a-graph-aware-language-model-framework | 12.8 | 89.59 | 22.77 | 52.06 |
| gap-a-graph-aware-language-model-framework | 34.02 | - | 26.93 | 62.9 |
| eventnarrative-a-large-scale-event-centric | 30.78 | 92.12 | 27.72 | 71.92 |
| gap-a-graph-aware-language-model-framework | 31.19 | 93.68 | 26.58 | 64.91 |
| eventnarrative-a-large-scale-event-centric | 12.8 | 89.59 | 22.77 | 52.06 |
| eventnarrative-a-large-scale-event-centric | 31.38 | 93.12 | 26.68 | 62.65 |
| gap-a-graph-aware-language-model-framework | 31.38 | 93.12 | 26.68 | 62.65 |