ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2017, Vol. 54 ›› Issue (8): 1682-1692.doi: 10.7544/issn1000-1239.2017.20170200

所属专题: 2017人工智能前沿进展专题

• 人工智能 • 上一篇    下一篇



  1. (电子科技大学信息与软件工程学院 成都 610054) (
  • 出版日期: 2017-08-01
  • 基金资助: 

Representation Learning Based Relational Inference Algorithm with Semantical Aspect Awareness

Liu Qiao, Han Minghao, Yang Xiaohui, Liu Yao, Wu Zufeng   

  1. (School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054)
  • Online: 2017-08-01

摘要: 基于知识表示的关系推理方法研究是近年来统计关系学习和知识图谱领域共同关注的热点.通过对当前流行的基于知识表示的推理模型进行比较,分析了现有模型所普遍采用的基本假设存在的不合理之处,即忽视了实体与关系在语义上的多样性.据此提出了一种新的关系推理建模假设:实体对之间的每种关系反映的是两侧实体在某些特定方面的语义关联,通过对实体向量的语义方面要素进行选择性加权,可以实现对不同关系语义的表示和区分.根据该假设提出了一种新的关系推理建模方法,采用非线性变换的方法来解决表示学习中的语义分辨率问题.在公开数据集上的实验结果表明:所提出的算法对复杂关系类型和相关实体具有良好的语义区分能力,能有效提高知识图谱上的关系推理准确率,性能显著优于目前主流的相关工作.

关键词: 统计关系学习, 关系推理, 表示学习, 知识图谱, 多元关系数据挖掘

Abstract: Knowledge representation based relational inference algorithms is a crucial research issue in the field of statistical relational learning and knowledge graph population in recent years. In this work, we perform a comparative study of the prevalent knowledge representation based reasoning models, with detailed discussion of the general potential problems contained in their basic assumptions. The major problem of these representation based relational inference models is that they often ignore the semantical diversity of entities and relations, which will cause the lack of semantic resolution to distinguish them, especially when there exists more than one type of relation between two given entities. This paper proposes a new assumption for relation reasoning in knowledge graphs, which claims that each of the relations between any entity pairs reflects the semantical connection of some specific attention aspects of the corresponding entities, and could be modeled by selectively weighting on the constituent of the embeddings to help alleviating the semantic resolution problem. A semantical aspect aware relational inference algorithm is proposed to solve the semantic resolution problem, in which a nonlinear transformation mechanism is introduced to capture the effects of the different semantic aspects of the embeddings. Experimental results on public datasets show that the proposed algorithms have superior semantic discrimination capability for complex relation types and their associated entities, which can effectively improve the accuracy of relational inference on knowledge graphs, and the proposed algorithm significantly outperforms the state-of-the-art approaches.

Key words: statistical relational learning, relational inference, representation learning, knowledge graphs, multi-relational data mining