基于分布式表示和多特征融合的知识库三元组分类

三元组分类是知识库补全及关系抽取的重要技术。当前主流的三元组分类方法通常基于TransE来构建知识库实体和关系的分布式表示。然而, TransE方法仅仅适用于处理1对1类型的关系,无法很好的处理1对多、多对1及多对多类型的关系。针对上述问题,该文在分布式表示的基础上,提出了一种特征融合的方法—TCSF,通过综合利用三元组的距离、关系的先验概率及实体与关系上下文的拟合度进行三元组分类。在四种公开的数据集(WN11、WN18、FB13、FB15K)上的测试结果显示,TCSF在三元组分类上的效果超过现有的state-of-the-art模型。

Triple Classification Based on Synthesized Features for Knowledge Base

Triple classification is crucial for knowledge base completion and relation extraction. However, the state-of-the-art methods for triple classification fail to tackle 1-to-n, m-to-1 and m-to-n relations. In this paper, we propose TCSF (Triple Classification based on Synthesized Features) method, which can joint exploit the triple distance, the prior probability of relation, and the context compatibility between entity pair and relation for triple classification. Experimental results on four datasets (WN11, WN18, FB13, FB15K) show that TCSF can achieve significant improvement over TransE and other state-of-the-art triple classification approaches.