Text Summarization On Cnn Daily Mail 2
评估指标
ROUGE-1
ROUGE-2
ROUGE-L
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | ROUGE-1 | ROUGE-2 | ROUGE-L |
|---|---|---|---|
| generative-adversarial-network-for | 39.92 | 17.65 | 36.71 |
| summarunner-a-recurrent-neural-network-based | 39.6 | 16.2 | 35.3 |
| improving-abstraction-in-text-summarization | 40.02 | 15.53 | 37.44 |
| guiding-generation-for-abstractive-text | 38.95 | 17.12 | 35.68 |
| fastformer-additive-attention-is-all-you-need | 38.54 | 16.22 | 36.21 |
| fast-abstractive-summarization-with-reinforce | 39.66 | 15.85 | 37.34 |
| summarunner-a-recurrent-neural-network-based | 39.2 | 15.7 | 35.5 |
| learning-to-extract-coherent-summary-via-deep | 41.25 | 18.87 | 37.75 |
| extractive-summarization-with-swap-net | 41.6 | 18.3 | 37.7 |
| a-hierarchical-structured-self-attentive | 42.3 | 17.8 | 37.6 |
| abstractive-text-summarization-using-sequence | 35.46 | 13.30 | 32.65 |
| abstractive-document-summarization-with-a | 38.1 | 13.9 | 34.0 |
| a-deep-reinforced-model-for-abstractive | 39.87 | 15.82 | 36.90 |