Text Summarization On X Sum
評価指標
ROUGE-1
ROUGE-2
ROUGE-3
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 | ROUGE-1 | ROUGE-2 | ROUGE-3 |
|---|---|---|---|
| dont-give-me-the-details-just-the-summary | 29.79 | 8.81 | 22.66 |
| dont-give-me-the-details-just-the-summary | 31.89 | 11.54 | 25.75 |
| text-summarization-with-pretrained-encoders | 38.81 | 16.50 | 31.27 |
| dont-give-me-the-details-just-the-summary | 28.42 | 8.77 | 22.48 |
| bart-denoising-sequence-to-sequence-pre | 45.14 | 22.27 | 37.25 |
| brio-bringing-order-to-abstractive | 49.07 | 25.59 | 40.40 |
| palm-2-technical-report-1 | - | 16.9 | - |
| lift-yourself-up-retrieval-augmented-text | 50.30 | 26.70 | 41.60 |
| simcls-a-simple-framework-for-contrastive | 47.61 | 24.57 | - |
| summareranker-a-multi-task-mixture-of-experts-1 | 48.12 | 24.95 | - |
| dont-give-me-the-details-just-the-summary | 28.10 | 8.02 | 21.72 |
| palm-2-technical-report-1 | - | 23.2 | - |
| dont-give-me-the-details-just-the-summary | 15.16 | 1.78 | 11.27 |
| dont-give-me-the-details-just-the-summary | 16.30 | 1.60 | 11.95 |
| pegasus-pre-training-with-extracted-gap | 47.21 | 24.56 | - |
| hierarchical-learning-for-generation-with | 45.92 | 22.79 | - |
| dont-give-me-the-details-just-the-summary | 29.70 | 9.21 | 23.24 |
| palm-2-technical-report-1 | - | 17.2 | - |