Recent progress in sentence embedding, which represents the meaning of a sentence as a point in a vector space, has achieved high performance on tasks such as a semantic textual similarity (STS) task. However, sentence representations as a point in a vector space can express only a part of the diverse information that sentences have, such as asymmetrical relationships between sentences. This paper proposes GaussCSE, a Gaussian distribution-based contrastive learning framework for sentence embedding that can handle asymmetric relationships between sentences, along with a similarity measure for identifying inclusion relations. Our experiments show that GaussCSE achieves the same performance as previous methods in natural language inference tasks, and is able to estimate the direction of entailment relations, which is difficult with point representations.

翻译：近期在句子嵌入方面的进展，即把句子含义表示为向量空间中的一个点，已在语义文本相似度（STS）等任务上取得了高性能。然而，将句子表示为向量空间中的一个点，仅能表达句子所蕴含的多样信息的一部分，例如句子之间的非对称关系。本文提出GaussCSE，一种基于高斯分布的对比学习框架，用于处理句子间的非对称关系，并配套提出一种用于识别包含关系的相似性度量指标。实验表明，GaussCSE在自然语言推理任务中达到了与先前方法相同的性能，并且能够估计蕴含关系的方向，而这是点表征难以实现的。