Ccg Supertagging On Ccgbank
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Xu et al. | 93.00 | - | - |
| BiLSTM-LAN | 94.7 | Hierarchically-Refined Label Attention Network for Sequence Labeling | |
| Lewis et al. | 94.7 | - | - |
| CVT + Multi-task + Large | 96.1 | Semi-Supervised Sequence Modeling with Cross-View Training | |
| Heterogeneous Dynamic Convolutions | 96.29 | Geometry-Aware Supertagging with Heterogeneous Dynamic Convolutions | |
| NeST-CCG + BERT | 96.25 | Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks | |
| Low supervision | 93.26 | - | - |
| Vaswani et al. | 94.24 | - | - |
0 of 8 row(s) selected.