Question Answering On Babi
Métriques
Mean Error Rate
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Mean Error Rate |
|---|---|
| finding-remo-related-memory-object-a-simple | 1.2% |
| dynamic-neural-turing-machine-with-soft-and | - |
| tracking-the-world-state-with-recurrent | 9.7% |
| recurrent-relational-networks | 0.46% |
| scaling-memory-augmented-neural-networks-with | 6.4% |
| self-assttentive-associative-memory | 0.39% |
| neural-stored-program-memory | 5.6% |
| rotational-unit-of-memory | - |
| gated-orthogonal-recurrent-units-on-learning | - |
| end-to-end-memory-networks | 7.5% |
| h-mem-harnessing-synaptic-plasticity-with | - |
| memory-enriched-computation-and-learning-in | - |
| scaling-memory-augmented-neural-networks-with | 28.7% |
| query-reduction-networks-for-question | 0.3% |