Extractive Document Summarization On
評価指標
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-L | Paper Title | Repository |
|---|---|---|---|
| BERT-Large | 49.98 | DebateSum: A large-scale argument mining and summarization dataset | - |
| Longformer-Base | 57.21 | DebateSum: A large-scale argument mining and summarization dataset | - |
| GPT2-Medium | 53.23 | DebateSum: A large-scale argument mining and summarization dataset | - |
0 of 3 row(s) selected.