论文标题
与及时衍生的虚拟语义原型的对比度学习，用于无监督的句子
Contrastive Learning with Prompt-derived Virtual Semantic Prototypes for Unsupervised Sentence Embedding
论文作者
论文摘要
对比学习已成为无监督句子嵌入的新范式。先前的研究着重于实例对比度学习，试图用文本数据扩展构建积极对。在本文中，我们提出了一种新颖的对比学习方法，该方法具有迅速的虚拟语义原型（CONPVP）。具体而言，在提示的帮助下，我们为每个实例构建虚拟语义原型，并通过使用提示的负面形式来得出负面原型。使用原型对比损失，我们强制执行嵌入的锚定句子接近其相应的语义原型，并且与负原型以及其他句子的原型相距甚远。关于语义文本相似性，转移和聚类任务的广泛实验结果与强基础相比，我们提出的模型的有效性证明了我们所提出的模型的有效性。代码可在https://github.com/lemon0830/promptcse上找到。
Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation. In this paper, we propose a novel Contrastive learning method with Prompt-derived Virtual semantic Prototypes (ConPVP). Specifically, with the help of prompts, we construct virtual semantic prototypes to each instance, and derive negative prototypes by using the negative form of the prompts. Using a prototypical contrastive loss, we enforce the anchor sentence embedding to be close to its corresponding semantic prototypes, and far apart from the negative prototypes as well as the prototypes of other sentences. Extensive experimental results on semantic textual similarity, transfer, and clustering tasks demonstrate the effectiveness of our proposed model compared to strong baselines. Code is available at https://github.com/lemon0830/promptCSE.
