Cross Lingual Natural Language Inference On 1
評価指標
Accuracy
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 | Accuracy |
|---|---|
| bert-pre-training-of-deep-bidirectional | 74.3% |
| supervised-learning-of-universal-sentence | 60.7% |
| supervised-learning-of-universal-sentence | 68.7% |
| better-fine-tuning-by-reducing | 85.2% |