Unsupervised sentence representation learning aims to transform input sentences into fixed-length vectors enriched with intricate semantic information while obviating the reliance on labeled data. Recent strides within this domain have been significantly propelled by breakthroughs in contrastive learning and prompt engineering. Despite these advancements, the field has reached a plateau, leading some researchers to incorporate external components to enhance the quality of sentence embeddings. Such integration, though beneficial, complicates solutions and inflates demands for computational resources. In response to these challenges, this paper presents CoT-BERT, an innovative method that harnesses the progressive thinking of Chain-of-Thought reasoning to tap into the latent potential of pre-trained models like BERT. Additionally, we develop an advanced contrastive learning loss function and propose a novel template denoising strategy. Rigorous experimentation demonstrates that CoT-BERT surpasses a range of well-established baselines by relying exclusively on the intrinsic strengths of pre-trained models.

翻译：无监督句子表示学习旨在将输入句子转换为富含复杂语义信息的固定长度向量，同时避免对标注数据的依赖。该领域近期的显著进展主要得益于对比学习和提示工程的突破。尽管取得了这些进步，该领域的发展已进入平台期，促使一些研究者引入外部组件以提升句子嵌入的质量。此类集成虽有益处，却使解决方案复杂化并增加了对计算资源的需求。针对这些挑战，本文提出了CoT-BERT，这是一种创新方法，它利用思维链推理的渐进式思维来挖掘如BERT等预训练模型的潜在能力。此外，我们开发了一种先进的对比学习损失函数，并提出了一种新颖的模板去噪策略。严格的实验表明，CoT-BERT仅依靠预训练模型的内在优势，便超越了一系列公认的基线模型。