We present Relational Sentence Embedding (RSE), a new paradigm to further discover the potential of sentence embeddings. Prior work mainly models the similarity between sentences based on their embedding distance. Because of the complex semantic meanings conveyed, sentence pairs can have various relation types, including but not limited to entailment, paraphrasing, and question-answer. It poses challenges to existing embedding methods to capture such relational information. We handle the problem by learning associated relational embeddings. Specifically, a relation-wise translation operation is applied to the source sentence to infer the corresponding target sentence with a pre-trained Siamese-based encoder. The fine-grained relational similarity scores can be computed from learned embeddings. We benchmark our method on 19 datasets covering a wide range of tasks, including semantic textual similarity, transfer, and domain-specific tasks. Experimental results show that our method is effective and flexible in modeling sentence relations and outperforms a series of state-of-the-art sentence embedding methods. https://github.com/BinWang28/RSE

翻译：我们提出关系型句子嵌入（Relational Sentence Embedding, RSE），这是一种进一步挖掘句子嵌入潜力的新范式。先前的工作主要基于句子嵌入距离来建模句子之间的相似性。由于句子所传达的复杂语义含义，句子对可以具有多种关系类型，包括但不限于蕴涵、释义和问答。这对现有嵌入方法捕获此类关系信息提出了挑战。我们通过学习关联关系嵌入来处理这一问题。具体而言，我们对源句子应用关系导向的平移操作，利用预训练的基于孪生网络的编码器来推断对应的目标句子。精细粒度的关系相似度分数可以从学习到的嵌入中计算得出。我们在涵盖广泛任务的19个数据集上对我们的方法进行了基准测试，包括语义文本相似性、迁移和领域特定任务。实验结果表明，我们的方法在建模句子关系方面有效且灵活，并超越了一系列最先进的句子嵌入方法。https://github.com/BinWang28/RSE