SBERT-NLI-large

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

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

Natural Language Processing4 results

Semantic Textual SimilarityonSTS14
Spearman Correlation· 2019-08-27
0.7490000000000001
best: 0.8689 (AnglE-LLaMA-13B)
SOTA
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks arXiv:1908.10084
Semantic Textual SimilarityonSTS13
Spearman Correlation· 2019-08-27
0.7846
best: 0.9058 (AnglE-LLaMA-7B)
SOTA
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks arXiv:1908.10084
Semantic Textual SimilarityonSICK
Spearman Correlation· 2019-08-27
0.7375
best: 0.8243 (PromCSE-RoBERTa-large (0.355B))
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks arXiv:1908.10084
Semantic Textual SimilarityonSTS Benchmark
Spearman Correlation· 2019-08-27
0.79
best: 0.931 (Mnet-Sim)
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks arXiv:1908.10084