Question Answering On Semevalcqa
Metriken
MAP
P@1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | MAP | P@1 |
|---|---|---|
| kelp-at-semeval-2016-task-3-learning-semantic | 0.792 | 0.751 |
| attentive-pooling-networks | 0.771 | 0.755 |
| convkn-at-semeval-2016-task-3-answer-and | 0.777 | 0.755 |
| convolutional-neural-network-architectures-1 | 0.780 | 0.753 |
| hyperbolic-representation-learning-for-fast | 0.795 | 0.809 |