Knowledge graphs, on top of entities and their relationships, contain other important elements: literals. Literals encode interesting properties (e.g. the height) of entities that are not captured by links between entities alone. Most of the existing work on embedding (or latent feature) based knowledge graph analysis focuses mainly on the relations between entities. In this work, we study the effect of incorporating literal information into existing link prediction methods. Our approach, which we name LiteralE, is an extension that can be plugged into existing latent feature methods. LiteralE merges entity embeddings with their literal information using a learnable, parametrized function, such as a simple linear or nonlinear transformation, or a multilayer neural network. We extend several popular embedding models based on LiteralE and evaluate their performance on the task of link prediction. Despite its simplicity, LiteralE proves to be an effective way to incorporate literal information into existing embedding based methods, improving their performance on different standard datasets, which we augmented with their literals and provide as testbed for further research.
翻译:以实体及其关系为顶端的知识图表包含其他重要元素: 字面文字。 字面文字将实体不单由实体之间的联系所捕捉的有趣的属性( 高度) 编码成字面文字。 大多数基于嵌入( 潜在特征) 知识图表分析的现有工作主要侧重于实体之间的关系。 在这项工作中, 我们研究将字面信息纳入现有链接预测方法的效果。 我们命名LiteralE 的方法是一个可以插入现有潜在特征方法的延伸。 字面E 合并了实体, 以其字面信息嵌入它们的字面信息, 使用简单、 线性或非线性变换或多层线性线性线性网络等可学习的功能。 我们扩展了几个基于LiteralE 的流行嵌入模型, 并评估其在连接预测任务上的性能。 尽管它简单, 字面E 证明它是一个有效的方法, 将字面信息融入现有的嵌入方法, 改进它们在不同的标准数据集上的性能, 我们用它们的性能加以扩展, 并提供进一步的研究试验床 。