中文摘要：

现有张量分解技术在用于知识图谱学习和推理过程中时，只考虑知识图谱中实体与实体间的直接关系，忽略知识图谱图形结构的特点．因此，文中提出基于路径张量分解的知识图谱推理算法（PRESCAL），利用路径排列算法（PRA）获得知识图谱中各实体对间的关系路径．然后对实体对间的关系路径进行张量分解，并在优化更新过程中采用交替最小二乘法．实验表明，在路径问题回答任务和实体链接预测任务中，PRESCAL可以取得较好的预测准确率．

英文摘要：

In the existing tensor factorization techniques used in knowledge graph learning and reasoning, only direct links between entities are taken into account. However, the graph structure of knowledge graph is ignored. In this paper, knowledge graph reasoning based on paths of tensor factorization is proposed. The path ranking algorithm（PRA） is employed to find all paths connecting the source and target nodes in a relation instances. Then, those paths are decomposed by tensor factorization. And the entities and relations are optimized by the alternating least squares method. Experimental resuhs on two large-scale knowledge graphs show the algorithm achieves significant and consistent improvement on tasks of entities linking prediction and paths question answering and its prediction accuracy outperforms that of other related models.