Unsupervised Extractive Summarization On 1
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 |
|---|---|---|---|---|---|
| Lead | 35.63 | 12.28 | 25.17 | - | - |
| LexRank | 39.19 | 13.89 | 34.59 | A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents | |
| SumBasic | 37.15 | 11.36 | 33.43 | A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents | |
| TextRank | 38.66 | 15.87 | 34.53 | - | - |
| FAR | 41.98 | 15.66 | 37.58 | - | - |
| MMR | 37.65 | 10.61 | 33.71 | - | - |
| LSA | 33.89 | 9.93 | 29.70 | A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents | |
| PacSum | 39.79 | 14.00 | 36.09 | Discourse-Aware Unsupervised Summarization of Long Scientific Documents | |
| HipoRank | 43.58 | 17.00 | 39.31 | Discourse-Aware Unsupervised Summarization of Long Scientific Documents |
0 of 9 row(s) selected.