Data To Text Generation On Rotowire
Metrics
BLEU
Results
Performance results of various models on this benchmark
Model Name | BLEU | Paper Title | Repository |
|---|---|---|---|
| Hierarchical transformer encoder + conditional copy | 17.50 | A Hierarchical Model for Data-to-Text Generation | |
| HierarchicalEncoder + NR + IR | 17.96 | Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation | |
| Macro | 15.46 | Data-to-text Generation with Macro Planning | |
| Neural Content Planning + conditional copy | 16.50 | Data-to-Text Generation with Content Selection and Planning | |
| Encoder-decoder + conditional copy | 14.19 | Challenges in Data-to-Document Generation | |
| Force-Copy | 17.26 | May the Force Be with Your Copy Mechanism: Enhanced Supervised-Copy Method for Natural Language Generation | - |
0 of 6 row(s) selected.