Question Answering On Tempquestions
评估指标
F1
Hits@1
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 | F1 | Hits@1 |
|---|---|---|
| semantic-framework-based-query-generation-for | 41.1 | 41.2 |
| quint-interpretable-question-answering-over | 28.8 | 27 |
| question-answering-as-programming-for-solving | 68.1 | - |
| 模型 4 | 60.1 | - |
| tequila-temporal-question-answering-over | 32 | 31.7 |
| 模型 6 | 44.6 | - |
| tequila-temporal-question-answering-over | 37.5 | 36.2 |
| more-accurate-question-answering-on-freebase | 27.2 | 24.9 |