Question Answering On Semevalcqa
Metriken
MAP
P@1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | MAP | P@1 | Paper Title | Repository |
|---|---|---|---|---|
| Kelp | 0.792 | 0.751 | - | - |
| AP-CNN | 0.771 | 0.755 | Attentive Pooling Networks | |
| ConvKN | 0.777 | 0.755 | - | - |
| ARC-II | 0.780 | 0.753 | Convolutional Neural Network Architectures for Matching Natural Language Sentences | |
| HyperQA | 0.795 | 0.809 | Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering |
0 of 5 row(s) selected.