Semantic Parsing On Spider
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| lever-learning-to-verify-language-to-code | 81.9 |
| picard-parsing-incrementally-for-constrained | 71.9 |
| rat-sql-relation-aware-schema-encoding-and-1 | 65.6 |
| decoupling-the-skeleton-parsing-and-schema | 84.1 |
| spider-a-large-scale-human-labeled-dataset | 19.7 |
| graphix-t5-mixing-pre-trained-transformers | 74.0 |
| sadga-structure-aware-dual-graph-aggregation | 70.1 |
| rasat-integrating-relational-structures-into | 75.5 |
| learning-contextual-representations-for | 69.7 |
| grappa-grammar-augmented-pre-training-for | 69.6 |