Natural Language Generation on Laptop RNNLG benchmark (test)
52.38BLEUDeep Ensemble Model
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Deep Ensemble Modeltype=ensemble2018.05 | 52.38 | 155 | |
| CNN2018.05 | 52.31 | 225 | |
| SCLSTM2018.05 | 51.16 | 79 | |
| LSTM2018.05 | 50.83 | 443 |
| Method | Links | ||
|---|---|---|---|
| Deep Ensemble Modeltype=ensemble2018.05 | 52.38 | 155 | |
| CNN2018.05 | 52.31 | 225 | |
| SCLSTM2018.05 | 51.16 | 79 | |
| LSTM2018.05 | 50.83 | 443 |