Table 2 Ablation studies of our model on the test set
From: Multi-task learning for abstractive text summarization with key information guide network
Model | ROUGE-1 | ROUGE-2 | ROUGE-L |
|---|---|---|---|
Our model | 39.15 | 17.34 | 35.92 |
W/o prediction-guide | 38.16 | 17.17 | 34.95 |
W/o key information extraction | 37.25 | 16.15 | 34.19 |
W/o pointer network | 37.83 | 16.52 | 34.68 |
W/o joint training | 36.35 | 15.62 | 33.38 |