Semantic Textual Similarity on CDSC-R (val)
88.28Spearman CorrelationDiffAug + MixSP
Evaluation results
| Method | Links | |
|---|---|---|
| DiffAug + MixSPEncoder Architecture=BERT-Base, Base Method=DiffAug, Training Strategy=MixSP2024.06 | 88.28 | |
| SimCSE + MixSPEncoder Architecture=BERT-Base, Base Method=SimCSE, Training Strategy=MixSP2024.06 | 88.27 | |
| DiffAug + MoEEncoder Architecture=BERT-Base, Base Method=DiffAug, Training Strategy=MoE2024.06 | 86.29 | |
| DiffAug + MixSPEncoder Architecture=RoBERTa-Base, Base Method=DiffAug, Training Strategy=MixSP2024.06 | 86.16 | |
| SBERT + MixSPEncoder Architecture=RoBERTa-Base, Base Method=SBERT, Training Strategy=MixSP2024.06 | 85.6 | |
| SBERT + MoEEncoder Architecture=RoBERTa-Base, Base Method=SBERT, Training Strategy=MoE2024.06 | 85.09 | |
| SBERT + MixSPEncoder Architecture=BERT-Base, Base Method=SBERT, Training Strategy=MixSP2024.06 | 85.08 | |
| DiffAug + MoEEncoder Architecture=RoBERTa-Base, Base Method=DiffAug, Training Strategy=MoE2024.06 | 85.01 | |
| SBERT + MoEEncoder Architecture=BERT-Base, Base Method=SBERT, Training Strategy=MoE2024.06 | 84.7 | |
| SimCSE + MixSPEncoder Architecture=RoBERTa-Base, Base Method=SimCSE, Training Strategy=MixSP2024.06 | 84.48 | |
| SimCSE + MoEEncoder Architecture=RoBERTa-Base, Base Method=SimCSE, Training Strategy=MoE2024.06 | 84.01 | |
| SimCSE + MoEEncoder Architecture=BERT-Base, Base Method=SimCSE, Training Strategy=MoE2024.06 | 82.87 | |
| SimCSEEncoder Architecture=BERT-Base, Base Method=SimCSE, Training Strategy=Base2024.06 | 70.21 | |
| SimCSE + FTEncoder Architecture=BERT-Base, Base Method=SimCSE, Training Strategy=FT2024.06 | 69.98 | |
| SimCSE + FTEncoder Architecture=RoBERTa-Base, Base Method=SimCSE, Training Strategy=FT2024.06 | 69.01 | |
| SimCSEEncoder Architecture=RoBERTa-Base, Base Method=SimCSE, Training Strategy=Base2024.06 | 68.38 | |
| SBERTEncoder Architecture=RoBERTa-Base, Base Method=SBERT, Training Strategy=Base2024.06 | 68.37 | |
| DiffAug + FTEncoder Architecture=BERT-Base, Base Method=DiffAug, Training Strategy=FT2024.06 | 67.91 | |
| DiffAug + FTEncoder Architecture=RoBERTa-Base, Base Method=DiffAug, Training Strategy=FT2024.06 | 64.14 | |
| DiffAugEncoder Architecture=RoBERTa-Base, Base Method=DiffAug, Training Strategy=Base2024.06 | 62.47 | |
| DiffAugEncoder Architecture=BERT-Base, Base Method=DiffAug, Training Strategy=Base2024.06 | 61.42 | |
| SBERTEncoder Architecture=BERT-Base, Base Method=SBERT, Training Strategy=Base2024.06 | 59.48 |