Relation Classification On Tacred 1
評価指標
F1
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
比較表
| モデル名 | F1 |
|---|---|
| ernie-enhanced-language-representation-with | 66.0 |
| structured-prediction-as-translation-between-1 | 61.9 |
| luke-deep-contextualized-entity | 72.7 |
| zero-shot-information-extraction-as-a-unified | 76.4 |
| knowledge-enhanced-contextual-word | 71.5 |
| zero-shot-information-extraction-as-a-unified | 49.2 |
| matching-the-blanks-distributional-similarity | 71.5 |
| deepstruct-pretraining-of-language-models-for-1 | 36.1 |
| spanbert-improving-pre-training-by | 70.8 |
| k-adapter-infusing-knowledge-into-pre-trained | 71.3 |
| deepstruct-pretraining-of-language-models-for-1 | 76.8 |
| ernie-enhanced-language-representation-with | 68.0 |
| deepstruct-pretraining-of-language-models-for-1 | 74.9 |
| structured-prediction-as-translation-between-1 | 71.9 |
| kepler-a-unified-model-for-knowledge | 71.7 |
| graph-convolution-over-pruned-dependency | 66.4 |
| k-adapter-infusing-knowledge-into-pre-trained | 72.0 |