Cross Lingual Natural Language Inference On 3
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Accuracy |
|---|---|
| better-fine-tuning-by-reducing | 84.2% |
| bert-pre-training-of-deep-bidirectional | 70.5% |
| supervised-learning-of-universal-sentence | 67.7% |
| supervised-learning-of-universal-sentence | 61.0% |