Natural Language Inference on Breaking NLI (test)
67.4AccuracyOM
Evaluation results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OMModel Type=Sequence Encoder2023.11 | 67.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| BBT-GRCModel Type=Sequence Encoder2023.11 | 65.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RIR-GRCModel Type=Sequence Encoder2023.11 | 57.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EBT-GRCModel Type=Sequence Encoder2023.11 | 55.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CRvNNModel Type=Sequence Encoder2023.11 | 55.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RIR-EBT-GRCModel Type=Sequence Encoder2023.11 | 55.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| BT-GRC OSModel Type=Sequence Encoder2023.11 | 53.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| BT-GRCModel Type=Sequence Encoder2023.11 | 51.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Decomp. Attn2018.08 | — | 41.6 | 55.1 | 53.5 | 85 | 15.2 | 52.9 | 96.9 | 65.2 | 37.5 | 2.1 | 31.7 | 59.2 | 97.5 | 43.1 | 51.9 | |
| ESIM2018.08 | — | 70.4 | 74.6 | 75.5 | 96.1 | 25.4 | 63.7 | 90.8 | 89.7 | 35.9 | 21 | 3.3 | 69.4 | 99.7 | 31.2 | 65.6 | |
| HBMPEmbedding Dimension=600D2018.08 | — | 54.7 | 69.1 | 58.8 | 90.4 | 81.2 | 81.3 | 96.9 | 82.6 | 49.8 | 4.5 | 45 | 72.1 | 84.5 | 40.4 | 65.1 | |
| InferSent2018.08 | — | 51.6 | 63.7 | 49.4 | 90.6 | 77.2 | 85.1 | 98.5 | 81.6 | 47.3 | 7.4 | 75 | 76.3 | 99.6 | 39.5 | 65.6 | |
| KIM2018.08 | — | 86.5 | 78.8 | 93.4 | 98.3 | 70.8 | 96.6 | 96.9 | 98.7 | 73.5 | 56.6 | 5 | 77.6 | 92.1 | 79.8 | 83.5 | |
| WordNet Baseline2018.08 | — | 95.5 | 94.5 | 98.6 | 98.7 | 100 | 94.8 | 67.7 | 75.3 | 78.5 | 40.7 | 100 | 89.9 | 70.5 | 86.2 | 85.8 |