SentenceBERT

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing1 result

Semantic Textual SimilarityonSICK
Spearman Correlation· uses extra data· 2019-08-27
0.7462
best: 0.8243 (PromCSE-RoBERTa-large (0.355B))
SOTA
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks arXiv:1908.10084