Papers › Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives...

Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives

6 Jun 2022arXiv:2206.02457archive 2025-07-28

Wei Wang, Liangzhu Ge, Jingqiao Zhang, Cheng Yang

Following SimCSE, contrastive learning based methods have achieved the state-of-the-art (SOTA) performance in learning sentence embeddings. However, the unsupervised contrastive learning methods still lag far behind the supervised counterparts. We attribute this to the quality of positive and negative samples, and aim to improve both. Specifically, for positive samples, we propose switch-case augmentation to flip the case of the first letter of randomly selected words in a sentence. This is to counteract the intrinsic bias of pre-trained token embeddings to frequency, word cases and subwords. For negative samples, we sample hard negatives from the whole dataset based on a pre-trained language model. Combining the above two methods with SimCSE, our proposed Contrastive learning with Augmented and Retrieved Data for Sentence embedding (CARDS) method significantly surpasses the current SOTA on STS benchmarks in the unsupervised setting.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

alibaba/simcse-with-cards officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AttributeContrastive LearningLanguage ModelingLanguage ModellingSTSSentenceSentence EmbeddingSentence EmbeddingsSentence-Embedding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningFLIPSimCSE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections