Summarization on EMAILSUM short 1.0 (test)
39.04R1Oracle
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Oracle2021.07 | 39.04 | 12.47 | 30.17 | 35.61 | 22.32 | |
| SemiSuptogetherBase Model=T5-base, Learning Paradigm=Semi-supervised, Unlabeled Data Source=Together (W3C + Avocado)2021.07 | 36.98 | 11.21 | 28.76 | 33.7 | 33.91 | |
| SemiSupavocadoBase Model=T5-base, Learning Paradigm=Semi-supervised, Unlabeled Data Source=Avocado2021.07 | 36.73 | 10.82 | 28.44 | 33.25 | 33.76 | |
| T5baseBase Model=T5-base, Learning Paradigm=Supervised, Model Architecture=Non-hierarchical2021.07 | 36.57 | 10.56 | 28.3 | 32.76 | 33.9 | |
| Hier. T5baseBase Model=T5-base, Model Architecture=Hierarchical2021.07 | 36.17 | 10.37 | 28.44 | 33.34 | 33.39 | |
| XSumpreBase Model=T5-base, Transfer Learning Source Dataset=XSum, Training Strategy=Pre-finetuning2021.07 | 36.14 | 10.26 | 28.66 | 33.47 | 33.97 | |
| CRD3preBase Model=T5-base, Transfer Learning Source Dataset=CRD3, Training Strategy=Pre-finetuning2021.07 | 36.05 | 10.04 | 27.21 | 32.06 | 33.52 | |
| SAMSumjointBase Model=T5-base, Transfer Learning Source Dataset=SAMSum, Training Strategy=Joint-training2021.07 | 35.57 | 10.07 | 27.95 | 32.57 | 33.55 | |
| CNNDMpreBase Model=T5-base, Transfer Learning Source Dataset=CNN/DM, Training Strategy=Pre-finetuning2021.07 | 35.43 | 10.75 | 27.49 | 32.15 | 33.61 | |
| SemiSupw3cBase Model=T5-base, Learning Paradigm=Semi-supervised, Unlabeled Data Source=W3C2021.07 | 35.43 | 10.64 | 28.59 | 32.31 | 33.61 | |
| SAMSumpreBase Model=T5-base, Transfer Learning Source Dataset=SAMSum, Training Strategy=Pre-finetuning2021.07 | 34.68 | 10.56 | 26.62 | 31.22 | 33.25 | |
| CRD3jointBase Model=T5-base, Transfer Learning Source Dataset=CRD3, Training Strategy=Joint-training2021.07 | 34.66 | 8.81 | 26.95 | 31.59 | 33.29 | |
| CNNDMjointBase Model=T5-base, Transfer Learning Source Dataset=CNN/DM, Training Strategy=Joint-training2021.07 | 34.38 | 9.27 | 27.2 | 31.3 | 32.7 | |
| XSumjointBase Model=T5-base, Transfer Learning Source Dataset=XSum, Training Strategy=Joint-training2021.07 | 34.18 | 8.17 | 25.94 | 30.68 | 31.83 | |
| Fast Abs RL2021.07 | 31.15 | 6.59 | 22.73 | 29.03 | 6.49 | |
| Lead-1-Email2021.07 | 26.62 | 5.6 | 19.72 | 23.77 | 13 | |
| BertSumExt2021.07 | 24.84 | 5.15 | 17.81 | 21.81 | 7.51 | |
| Lead-12021.07 | 23.35 | 5.57 | 18.22 | 19.61 | 12.25 | |
| TextRank2021.07 | 22.52 | 4.54 | 16.56 | 20.24 | 5.89 |