SCD: Self-Contrastive Decorrelation for Sentence Embeddings
This addresses the need for efficient and robust self-supervised learning in natural language processing, though it appears incremental as it builds on existing contrastive methods.
The paper tackles the problem of learning sentence embeddings without contrastive pairs by proposing Self-Contrastive Decorrelation (SCD), a self-supervised method that achieves comparable results with state-of-the-art methods on multiple benchmarks.
In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach. Given an input sentence, it optimizes a joint self-contrastive and decorrelation objective. Learning a representation is facilitated by leveraging the contrast arising from the instantiation of standard dropout at different rates. The proposed method is conceptually simple yet empirically powerful. It achieves comparable results with state-of-the-art methods on multiple benchmarks without using contrastive pairs. This study opens up avenues for efficient self-supervised learning methods that are more robust than current contrastive methods.