Sentence embedding is an influential research topic in natural language processing (NLP). Generation of sentence vectors that reflect the intrinsic meaning of sentences is crucial for improving performance in various NLP tasks. Therefore, numerous supervised and unsupervised sentence-representation approaches have been proposed since the advent of the distributed representation of words. These approaches have been evaluated on semantic textual similarity (STS) tasks designed to measure the degree of semantic information preservation; neural network-based supervised embedding models typically deliver state-of-the-art performance. However, these models have limitations in that they have numerous learnable parameters and thus require large amounts of specific types of labeled training data. Pretrained language model-based approaches, which have become a predominant trend in the NLP field, alleviate this issue to some extent; however, it is still necessary to collect sufficient labeled data for the fine-tuning process is still necessary. Herein, we propose an efficient approach that learns a transition matrix tuning a sentence embedding vector to capture the latent semantic meaning. Our proposed method has two practical advantages: (1) it can be applied to any sentence embedding method, and (2) it can deliver robust performance in STS tasks with only a few training examples.

句子嵌入是自然语言处理（NLP）中一个有影响力的研究课题。生成反映句子内在含义的句子向量对于提高各种 NLP 任务的性能至关重要。因此，自从单词的分布式表示出现以来，已经提出了许多有监督和无监督的句子表示方法。这些方法已经在旨在测量语义信息保留程度的语义文本相似性 (STS) 任务上进行了评估；基于神经网络的监督嵌入模型通常提供最先进的性能。然而，这些模型的局限性在于它们有许多可学习的参数，因此需要大量特定类型的标记训练数据。基于预训练语言模型的方法，成为NLP领域的主流趋势，一定程度上缓解了这个问题；然而，仍然需要收集足够的标记数据，用于微调过程仍然是必要的。在这里，我们提出了一种有效的方法，该方法可以学习调整句子嵌入向量的转换矩阵以捕获潜在语义。我们提出的方法有两个实际优势：（1）它可以应用于任何句子嵌入方法，（2）它可以在 STS 任务中提供稳健的性能，只需几个训练示例。我们提出了一种有效的方法，该方法可以学习调整句子嵌入向量的转换矩阵以捕获潜在语义。我们提出的方法有两个实际优势：（1）它可以应用于任何句子嵌入方法，（2）它可以在 STS 任务中提供稳健的性能，只需几个训练示例。我们提出了一种有效的方法，该方法可以学习调整句子嵌入向量的转换矩阵以捕获潜在语义。我们提出的方法有两个实际优势：（1）它可以应用于任何句子嵌入方法，（2）它可以在 STS 任务中提供稳健的性能，只需几个训练示例。