Question Answering On Ms Marco
评估指标
BLEU-1
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 | BLEU-1 | Rouge-L |
|---|---|---|
| multi-style-generative-reading-comprehension | 43.77 | 52.2 |
| bidirectional-attention-flow-for-machine | 10.64 | 23.96 |
| a-deep-cascade-model-for-multi-document | 54.64 | 52.01 |
| multi-passage-machine-reading-comprehension | 54.37 | 51.63 |