Natural Language Inference On E Snli
Metrics
Accuracy
BLEU
Results
Performance results of various models on this benchmark
| Paper Title | |||
|---|---|---|---|
| UnitedSynT5 (3B) | 94.0 | - | First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI |
| UnitedSynT5 (335M) | 89.8 | - | First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI |
| ExplainThenPredictAttention (e-InferSent Bi-LSTM + Attention) | 81.71 | 27.58 | e-SNLI: Natural Language Inference with Natural Language Explanations |
0 of 3 row(s) selected.