SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives
Xu, Jiahao, Shao, Wei, Chen, Lihui, Liu, Lemao
–arXiv.org Artificial Intelligence
This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative pairs affects the model's performance. Therefore, we propose a simple yet effective method to deal with such type of noise. Secondly, we pinpoint the rank bottleneck of current solutions to feature corruption and propose a dimension-wise contrastive learning objective to address this issue. Both proposed methods are generic and can be applied to any contrastive learning based models for sentence embeddings. Experimental results on standard benchmarks demonstrate that combining both proposed methods leads to a gain of 1.8 points compared to the strong baseline SimCSE configured with BERT base. Furthermore, applying the proposed method to DiffCSE, another strong contrastive learning based baseline, results in a gain of 1.4 points.
arXiv.org Artificial Intelligence
Oct-20-2023
- Country:
- North America
- Cuba (0.04)
- United States
- Washington > King County
- Seattle (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > San Diego County
- San Diego (0.04)
- Washington > King County
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- Europe
- Italy > Sardinia (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Iceland > Capital Region
- Reykjavik (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Asia
- North America
- Genre:
- Research Report > New Finding (0.46)
- Technology: