Quaternion contains one real part and three imaginary parts, which provided a more expressive hypercomplex space for learning knowledge graph. Existing quaternion embedding models measure the plausibility of a triplet either through semantic matching or geometric distance scoring functions. However, it appears that semantic matching diminishes the separability of entities, while the distance scoring function weakens the semantics of entities. To address this issue, we propose a novel quaternion knowledge graph embedding model. Our model combines semantic matching with entity's geometric distance to better measure the plausibility of triplets. Specifically, in the quaternion space, we perform a right rotation on head entity and a reverse rotation on tail entity to learn rich semantic features. Then, we utilize distance adaptive translations to learn geometric distance between entities. Furthermore, we provide mathematical proofs to demonstrate our model can handle complex logical relationships. Extensive experimental results and analyses show our model significantly outperforms previous models on well-known knowledge graph completion benchmark datasets. Our code is available at https://github.com/llqy123/DaBR.

翻译：四元数包含一个实部和三个虚部，为知识图谱学习提供了更具表达力的超复数空间。现有四元数嵌入模型通过语义匹配或几何距离评分函数来衡量三元组的合理性。然而，语义匹配会削弱实体的可区分性，而距离评分函数则会弱化实体的语义信息。为解决这一问题，我们提出了一种新颖的四元数知识图谱嵌入模型。该模型结合语义匹配与实体几何距离，以更好地衡量三元组的合理性。具体而言，在四元数空间中，我们对头实体执行右旋转、对尾实体执行反向旋转以学习丰富的语义特征。随后，我们利用距离自适应平移来学习实体间的几何距离。此外，我们通过数学证明展示了本模型能够处理复杂的逻辑关系。大量实验结果与分析表明，我们的模型在知名知识图谱补全基准数据集上显著优于现有模型。代码发布于 https://github.com/llqy123/DaBR。