Unsupervised sentence representation learning endeavors to transform input sentences into fixed-length vectors enriched with intricate semantic information while obviating the reliance on labeled data. Recent strides in 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 sentence embeddings' quality. Such integration, though beneficial, complicates the solutions and inflates the demand 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 substantiates 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。该领域近年来的进展主要得益于对比学习和提示工程的突破性成果。尽管取得这些进步，该领域已进入瓶颈期，促使研究者引入外部组件来提升句子嵌入质量。这种整合虽有益处，却使解决方案复杂化并增加了计算资源需求。针对这些挑战，本文提出CoT-BERT这一创新方法，通过利用思维链推理的渐进思考机制，挖掘BERT等预训练模型的潜在能力。此外，我们开发了改进的对比学习损失函数，并提出新颖的模板去噪策略。严格实验证明，CoT-BERT仅依赖预训练模型的内在优势，便超越了多种经典基线方法。