Question Answering on TriviaQA Wiki domain, Verified (dev)
63.8EMMINIMAL (Our Selector)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MINIMAL (Our Selector)n sent=10.5, Acc=90.9, Sp=x6.62018.05 | 63.8 | 67 | |
| MINIMAL (Our Selector)n sent=20.4, Acc=95.3, Sp=x3.42018.05 | 63.8 | 67.7 | |
| TF-IDFn sent=20, Acc=85.5, Sp=x3.52018.05 | 62.9 | 67.3 | |
| FULLn sent=69, Acc=95.9, Sp=x1.02018.05 | 61.6 | 66.1 | |
| MINIMAL (Our Selector)n sent=5.0, Acc=84.9, Sp=x13.82018.05 | 61 | 65 | |
| TF-IDFn sent=10, Acc=79.9, Sp=x6.92018.05 | 59.8 | 64.8 | |
| Neural Cascades2018.05 | 58.9 | 62.5 | |
| Mnemonic Reader2018.05 | 54.5 | 59.5 | |
| TF-IDFn sent=5, Acc=73.0, Sp=x13.82018.05 | 54.1 | 60.4 | |
| Reading Twice2018.05 | 53.4 | 59.9 | |
| QANetModel Type=Single Model2018.04 | 53.3 | 59.2 | |
| AMANDA2018.01 | 52.86 | 58.74 | |
| MEMEN2018.05 | 49.3 | 55.8 | |
| MEMENModel Type=Single Model2018.04 | 49.3 | 55.8 | |
| MEMEN2018.01 | 49.28 | 55.83 | |
| BiDAF2018.01 | 47.47 | 53.7 | |
| BiDAFModel Type=Single Model2018.04 | 46.5 | 52.8 | |
| Classifier2018.01 | 24.91 | 29.43 | |
| ClassifierModel Type=Single Model2018.04 | 23.6 | 27.9 | |
| Random2018.01 | 14.81 | 23.31 | |
| RandomModel Type=Single Model2018.04 | 13.8 | 23.4 |