SimCSE and RankCSE

SimCSE is a foundational contrastive learning approach for sentence embeddings that RankCSE builds upon and extends by incorporating ranking-based objectives to improve representation quality.

SimCSE
63
Established
RankCSE
37
Emerging
Maintenance 0/25
Adoption 16/25
Maturity 25/25
Community 22/25
Maintenance 0/25
Adoption 8/25
Maturity 16/25
Community 13/25
Stars: 3,644
Forks: 534
Downloads: 162
Commits (30d): 0
Language: Python
License: MIT
Stars: 48
Forks: 7
Downloads: —
Commits (30d): 0
Language: Python
License: MIT
Stale 6m
Stale 6m No Package No Dependents

About SimCSE

princeton-nlp/SimCSE

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

Provides both unsupervised and supervised training approaches—unsupervised leverages dropout-based noise on unlabeled data, while supervised incorporates NLI entailment pairs as positives and contradictions as hard negatives. Integrates seamlessly with HuggingFace Transformers and offers efficient similarity search via optional Faiss support, with pre-trained checkpoints available across BERT and RoBERTa architectures.

About RankCSE

perceptiveshawty/RankCSE

Implementation of "RankCSE: Unsupervised Sentence Representation Learning via Learning to Rank" (ACL 2023)

Scores updated daily from GitHub, PyPI, and npm data. How scores work