This folder contains the codes and models for our sentence embedding research papers.
InfoCSE : ''InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings'' was accepted by EMNLP 2022 Findings.
ESimCSE : ''ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding'' was accepted by COLING 2022.
gsInfoNCE : ''Smoothed Contrastive Learning for Unsupervised Sentence Embedding'' was accepted by COLING 2022.
DistilCSE : ''Effective Knowledge Distillation For Contrastive Sentence Embeddings''.