Abstractive Summarization on ConvoSumm Email 1.0 (test)
41.46ROUGE-1BART
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| BARTInput representation=vanilla, Training points=2002021.06 | 41.46 | 13.76 | 37.7 | |
| BARTPre-trained Model=BART-large, Training Samples=200 points, Input Format=Vanilla2021.06 | 41.46 | 13.76 | 37.7 | |
| BART-arg-filteredInput representation=arg-filtered, Training points=2002021.06 | 40.32 | 12.97 | 36.9 | |
| BART-argPre-trained Model=BART-large, Training Samples=200 points, Input Format=Argument-mining input2021.06 | 40.32 | 12.97 | 36.9 | |
| BART-arg-graphInput representation=arg-graph, Training points=2002021.06 | 39.05 | 12.14 | 35.99 |