Text Summarization On Dialogsum
評価指標
Rouge1
Rouge2
RougeL
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 | Rouge1 | Rouge2 | RougeL |
|---|---|---|---|
| instructive-dialogue-summarization-with-query | 47.8 | 22.2 | 39.4 |
| mind-the-gap-injecting-commonsense-knowledge | 46.26 | 20.95 | 41.05 |
| omnivec-learning-robust-representations-with | 46.91 | 21.22 | 40.19 |
| omnivec2-a-novel-transformer-based-network | 47.6 | 22.1 | 41.4 |