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 progress within this field, propelled by contrastive learning and prompt engineering, has significantly bridged the gap between unsupervised and supervised strategies. Nonetheless, the potential utilization of Chain-of-Thought, remains largely untapped in this trajectory. To unlock the latent capabilities of pre-trained models, such as BERT, we propose a two-stage approach for sentence representation: comprehension and summarization. Subsequently, the output of the latter phase is harnessed as the embedding of the input sentence. For further performance enhancement, we introduce an extended InfoNCE Loss by incorporating the contrast between positive and negative instances. Additionally, we also refine the existing template denoising technique to better mitigate the perturbing influence of prompts on input sentences. Rigorous experimentation substantiates our method, CoT-BERT, transcending a suite of robust baselines without necessitating other text representation models or external databases.

翻译：无监督句子表示学习旨在将输入句子转化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。受对比学习和提示工程推动，该领域的最新进展已显著缩小了无监督与有监督策略之间的差距。然而，思维链的潜在应用在该研究路径中仍基本未被开发。为释放如BERT等预训练模型的潜在能力，我们提出了一种两阶段句子表示方法：理解与总结。随后，将后一阶段的输出作为输入句子的嵌入表示。为进一步提升性能，我们通过引入正负实例间的对比，扩展了InfoNCE损失函数。此外，我们还改进了现有模板去噪技术，以更好地缓解提示对输入句子的干扰影响。严格实验证明，我们的方法CoT-BERT在无需其他文本表示模型或外部数据库的情况下，超越了多个稳健基线模型。