Abstractive Text Summarization On Abstractive 1
評価指標
BERTScore
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
比較表
| モデル名 | BERTScore | ROUGE-1 | ROUGE-2 | ROUGE-L |
|---|---|---|---|---|
| bart-it-an-efficient-sequence-to-sequence | 71.06 | 32.88 | 15.53 | 26.7 |
| two-new-datasets-for-italian-language | - | 38.91 | - | - |
| two-new-datasets-for-italian-language | - | 23.96 | - | - |
| bart-it-an-efficient-sequence-to-sequence | 74.69 | 35.04 | 17.41 | 28.68 |
| bart-it-an-efficient-sequence-to-sequence | 75.86 | 38.91 | 21.41 | 32.08 |
| two-new-datasets-for-italian-language | - | 33.78 | - | - |
| two-new-datasets-for-italian-language | - | 21.03 | - | - |
| bart-it-an-efficient-sequence-to-sequence | 75.36 | 37.31 | 19.44 | 30.41 |