Relational Knowledge Prediction via Dynamic Bi-Mode Embedding

Relational Knowledge Prediction via Dynamic Bi-Mode Embedding
复制标题

通过动态双模式嵌入进行关系知识预测

DOI:
10.1109/access.2018.2832165
复制
发表时间:
2018
期刊:
影响因子:
3.9
通讯作者:
Xiao Weidong
Xiao Weidong
中科院分区:
计算机科学3区
文献类型:
--
作者:
Fang Yang;Zhao Xiang;Tan Zhen;Xiao Weidong

文献摘要

参考文献

相似文献

知识图是人工智能中的一个重要概念,具有广泛的现实应用。然而,他们目前正遭受不完整的问题,即,图中的关系知识可能还不能满足实际需要。为了解决这个问题,主流的解决方案建议使用组合模型或翻译模型来预测链接。然而,预测准确性仍然是特别令人关注的。在本文中,我们提出了一种新的方法,即Bi-Mult,它结合了组合模型和翻译模型的优点。Bi-Mult基于组合模型,这样一个实体(分别是关系)嵌入被分解为两部分,一部分是表示实体内(分别为关系)状态,另一个用于实体间(分别)。关系)状态,并且我们将这样的嵌入称为双模式嵌入。此外,双模式关系嵌入增强了关系与实体的交互,从而改善了对反对称关系的处理。此外,我们通过双模式实体嵌入将映射矩阵纳入翻译模型,以构建用于表达复杂关系的动态嵌入,例如“1-to-N”,“N-to-1”和“N-to-N”关系。在实验中,我们评估我们的方法的基准数据集和链接预测的任务,我们的方法被证明优于国家的最先进的方法一致和显着。
Knowledge graphs are a crucial concept in artificial intelligence with a wide spectrum of real-life applications. Nonetheless, they are currently suffering from the incompleteness issue, i.e., relational knowledge in the graphs may not yet meet the practical needs. To address this issue, mainstream solutions propose to predict links by using compositional models or translation models. However, the prediction accuracy is still of particular concern. In this paper, we propose a new method, namely, Bi-Mult, which combines the advantages of compositional models and translation models. Bi-Mult is based on the compositional model, such that an entity (resp. relation) embedding is decomposed into two parts, one is to represent intra-entity (resp. relation) state and the other is for inter-entity (resp. relation) state, and we call such embedding as bi-mode embedding. In addition, the bi-mode relation embedding enhances relation’s interaction with entities, resulting its improvement on handling antisymmetric relations. Moreover, we incorporate mapping matrices in translation models through bi-mode entity embedding to construct dynamic embeddings for expressing complex relations, such as “1-to-N”, “N-to-1,” and “N-to-N” relations. In experiments, we evaluate our method on the benchmark data sets and the task of link prediction, and our method is demonstrated to outperform state-of-the-art methods consistently and significantly.
DOI: 10.1145/2187836.2187874
发表时间: 2012-04
期刊: Proceedings of the 21st international conference on World Wide Web
影响因子: --
作者:
Maximilian Nickel;Volker Tresp;H. Kriegel
通讯作者: Maximilian Nickel;Volker Tresp;H. Kriegel
DOI: 10.3115/1075527.1075662
发表时间: 1992-02
期刊: --
影响因子: --
作者:
G. Miller
通讯作者: G. Miller
DOI: --
发表时间: 2006-07
期刊: --
影响因子: --
作者:
Charles Kemp;J. Tenenbaum;T. Griffiths;Takeshi Yamada;N. Ueda
通讯作者: Charles Kemp;J. Tenenbaum;T. Griffiths;Takeshi Yamada;N. Ueda
DOI: 10.3115/v1/p15-1067
发表时间: 2015-07
期刊: --
影响因子: --
作者:
Guoliang Ji;Shizhu He;Liheng Xu;Kang Liu;Jun Zhao
通讯作者: Guoliang Ji;Shizhu He;Liheng Xu;Kang Liu;Jun Zhao
DOI: --
发表时间: 2012-07
期刊: --
影响因子: --
作者:
R. Socher;Brody Huval;Christopher D. Manning;A. Ng
通讯作者: R. Socher;Brody Huval;Christopher D. Manning;A. Ng