Temporal Tagging On Tempeval 3
評価指標
Strict Detection (Pr.)
Strict Detection (Re.)
Relaxed Detection (F1)
Relaxed Detection (Pr.)
Relaxed Detection (Re.)
Strict Detection (F1)
Type
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 | Strict Detection (Pr.) | Strict Detection (Re.) | Relaxed Detection (F1) | Relaxed Detection (Pr.) | Relaxed Detection (Re.) | Strict Detection (F1) | Type | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|---|
| BERT-base | 81.83 | 79.56 | 90.08 | 91.37 | 88.84 | 80.67 | 82.00 | BERT got a Date: Introducing Transformers to Temporal Tagging | |
| B2B | 94.11 | 81.01 | 92.52 | 100 | 86.09 | 87.07 | 83.79 | BERT got a Date: Introducing Transformers to Temporal Tagging | |
| DateBERT | 82.72 | 85.79 | 92.60 | 90.95 | 94.35 | 84.21 | 86.21 | BERT got a Date: Introducing Transformers to Temporal Tagging | |
| R2R | 96.37 | 96.37 | 100 | 100 | 100 | 96.37 | 90.43 | BERT got a Date: Introducing Transformers to Temporal Tagging | |
| Lange et al. | - | - | - | - | - | - | - | Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text | - |
0 of 5 row(s) selected.