Trans-Encoder-BERT-base-cross (unsup.)

Reported on 3 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Semantic Textual SimilarityonSTS15
Spearman Correlation· 2021-09-27
0.8444
best: 0.9004 (PromptEOL+CSE+LLaMA-30B)
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations arXiv:2109.13059
Semantic Textual SimilarityonSICK
Spearman Correlation· 2021-09-27
0.6952
best: 0.8243 (PromCSE-RoBERTa-large (0.355B))
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations arXiv:2109.13059
Semantic Textual SimilarityonSTS13
Spearman Correlation· 2021-09-27
0.8559
best: 0.9058 (AnglE-LLaMA-7B)
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations arXiv:2109.13059