Data To Text Generation On Totto
評価指標
BLEU
PARENT
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | BLEU | PARENT | Paper Title | Repository |
|---|---|---|---|---|
| NCP+CC (Puduppully et al 2019) | 19.2 | 29.2 | ToTTo: A Controlled Table-To-Text Generation Dataset | |
| BERT-to-BERT | 44 | 52.6 | ToTTo: A Controlled Table-To-Text Generation Dataset | |
| LATTICE (T5-base) | 48.4 | 58.1 | Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning | |
| Pointer Generator | 41.6 | 51.6 | ToTTo: A Controlled Table-To-Text Generation Dataset | |
| T5-3B | 49.5 | 58.4 | Text-to-Text Pre-Training for Data-to-Text Tasks | |
| T5 | - | - | The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics | - |
0 of 6 row(s) selected.