SimCSE
Princeton UniversityTsinghua UniversitySemantic embeddingOpen weights
SimCSE is a semantic embedding model from Princeton University,Tsinghua University released in 2022.
About SimCSE
This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive objective,
Details
- Provider
- Princeton University,Tsinghua University
- Task
- Semantic embedding
- Released
- 2022-05-18
- Open weights
- Yes