论文标题
SCD：嵌入句子的自对比度去相关
SCD: Self-Contrastive Decorrelation for Sentence Embeddings
论文作者
论文摘要
在本文中，我们提出了一种自我对比的反相关（SCD），这是一种自我监督的方法。给定输入句子，它优化了联合自对比和去相关的目标。通过利用标准辍学的实例化，以不同的速度来实例化，可以促进学习表示形式。所提出的方法在概念上是简单但在经验上强大的。它通过在多个基准上的最新方法中实现了可比的结果，而无需使用对比对。这项研究为有效的自我监督学习方法开辟了途径，这些学习方法比当前的对比方法更强大。
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.
