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
比較表
| モデル名 | ROUGE-1 | ROUGE-2 | ROUGE-L |
|---|---|---|---|
| improving-unsupervised-extractive | 35.63 | 12.28 | 25.17 |
| a-discourse-aware-attention-model-for | 39.19 | 13.89 | 34.59 |
| a-discourse-aware-attention-model-for | 37.15 | 11.36 | 33.43 |
| improving-unsupervised-extractive | 38.66 | 15.87 | 34.53 |
| improving-unsupervised-extractive | 41.98 | 15.66 | 37.58 |
| improving-unsupervised-extractive | 37.65 | 10.61 | 33.71 |
| a-discourse-aware-attention-model-for | 33.89 | 9.93 | 29.70 |
| hiporank-incorporating-hierarchical-and | 39.79 | 14.00 | 36.09 |
| hiporank-incorporating-hierarchical-and | 43.58 | 17.00 | 39.31 |