Data To Text Generation On Rotowire Content 1
Metrics
Precision
Recall
Results
Performance results of various models on this benchmark
Model Name | Precision | Recall | Paper Title | Repository |
|---|---|---|---|---|
| Hierarchical Transformer Encoder + conditional copy | 39.47% | 51.64% | A Hierarchical Model for Data-to-Text Generation | |
| Encoder-decoder + conditional copy | 29.49% | 36.18% | Challenges in Data-to-Document Generation | |
| Force-Copy | 34.34% | 48.85% | May the Force Be with Your Copy Mechanism: Enhanced Supervised-Copy Method for Natural Language Generation | - |
| Neural Content Planning + conditional copy | 34.18% | 51.22% | Data-to-Text Generation with Content Selection and Planning | |
| Macro | 34.1% | 57.8% | Data-to-text Generation with Macro Planning |
0 of 5 row(s) selected.