Instance Smoothed Contrastive Learning for Unsupervised Sentence Embedding
This work provides an incremental improvement for researchers and practitioners in natural language processing by enhancing sentence embedding methods for semantic similarity tasks.
The paper tackled the problem of improving unsupervised sentence embeddings by addressing the limitation of instance-level embeddings in contrastive learning, which may hurt generalization, and achieved improvements of 2.05%, 1.06%, 1.16%, and 0.52% in Spearman's correlation on STS tasks compared to unsup-SimCSE across different base models.
Contrastive learning-based methods, such as unsup-SimCSE, have achieved state-of-the-art (SOTA) performances in learning unsupervised sentence embeddings. However, in previous studies, each embedding used for contrastive learning only derived from one sentence instance, and we call these embeddings instance-level embeddings. In other words, each embedding is regarded as a unique class of its own, whichmay hurt the generalization performance. In this study, we propose IS-CSE (instance smoothing contrastive sentence embedding) to smooth the boundaries of embeddings in the feature space. Specifically, we retrieve embeddings from a dynamic memory buffer according to the semantic similarity to get a positive embedding group. Then embeddings in the group are aggregated by a self-attention operation to produce a smoothed instance embedding for further analysis. We evaluate our method on standard semantic text similarity (STS) tasks and achieve an average of 78.30%, 79.47%, 77.73%, and 79.42% Spearman's correlation on the base of BERT-base, BERT-large, RoBERTa-base, and RoBERTa-large respectively, a 2.05%, 1.06%, 1.16% and 0.52% improvement compared to unsup-SimCSE.