Learning Entity and Relation Embeddings for Knowledge Graph Completion
Learning Entity and Relation Embeddings for Knowledge Graph Completion
复制标题
DOI：
10.1609/aaai.v29i1.9491
复制
发表时间：
2015-01
期刊：
影响因子：
--
通讯作者：
Yankai Lin;Zhiyuan Liu;Maosong Sun;Yang Liu;Xuan Zhu
中科院分区：
文献类型：
--
作者：
Yankai Lin;Zhiyuan Liu;Maosong Sun;Yang Liu;Xuan Zhu
知识图补全旨在进行实体之间的链接预测。在本文中，我们考虑知识图嵌入的方法。最近，TransE 和 TransH 等模型通过将关系视为从头实体到尾实体的转换来构建实体和关系嵌入。我们注意到这些模型只是将实体和关系放在同一语义空间内。事实上，一个实体可能有多个方面，各种关系可能集中在实体的不同方面，这使得公共空间不足以进行建模。在本文中，我们提出 TransR 在单独的实体空间和关系空间中构建实体和关系嵌入。之后，我们通过首先将实体从实体空间投影到相应的关系空间，然后在投影实体之间构建翻译来学习嵌入。在实验中，我们在三个任务上评估我们的模型，包括链接预测、三元分类和关系事实提取。实验结果表明，与 TransE 和 TransH 等最先进的基线相比，有显着且一致的改进。
Knowledge graph completion aims to perform link prediction between entities. In this paper, we consider the approach of knowledge graph embeddings. Recently, models such as TransE and TransH build entity and relation embeddings by regarding a relation as translation from head entity to tail entity. We note that these models simply put both entities and relations within the same semantic space. In fact, an entity may have multiple aspects and various relations may focus on different aspects of entities, which makes a common space insufficient for modeling. In this paper, we propose TransR to build entity and relation embeddings in separate entity space and relation spaces. Afterwards, we learn embeddings by first projecting entities from entity space to corresponding relation space and then building translations between projected entities. In experiments, we evaluate our models on three tasks including link prediction, triple classification and relational fact extraction. Experimental results show significant and consistent improvements compared to state-of-the-art baselines including TransE and TransH.