Abstractive Text Summarization On Vietnews
評価指標
Rouge-1
Rouge-2
Rouge-L
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 | Rouge-1 | Rouge-2 | Rouge-L | Paper Title | Repository |
|---|---|---|---|---|---|
| Kết quả nghiên cứu | 67.80 | 24.32 | 39.69 | - | - |
| mT5 | 58.05 | 26.76 | 37.38 | - | - |
| ViT5 large | 63.37 | 34.24 | 43.55 | ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation | |
| Transformer | 57.56 | 24.25 | 35.53 | - | - |
| ViT5 base | 62.77 | 33.16 | 42.75 | ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation | |
| mBART | 59.81 | 28.28 | 38.71 | - | - |
| BARTpho | 61.14 | 30.31 | 40.15 | BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese |
0 of 7 row(s) selected.