Learning to Complete Knowledge Graphs with Deep Sequential Models
Learning to Complete Knowledge Graphs with Deep Sequential Models
复制标题
学习用深度序列模型完成知识图
DOI:
10.1162/dint_a_00016
复制
发表时间:
2019-06
影响因子:
3.9
通讯作者:
Yuzhong Qu
中科院分区:
文献类型:
--
作者:
Lingbing Guo;Qingheng Zhang;Wei Hu;Zequn Sun;Yuzhong Qu
Knowledge graph (KG) completion aims at filling the missing facts in a KG, where a fact is typically represented as a triple in the form of (head, relation, tail). Traditional KG completion methods compel two-thirds of a triple provided (e.g., head and relation) to predict the remaining one. In this paper, we propose a new method that extends multi-layer recurrent neural networks (RNNs) to model triples in a KG as sequences. It obtains state-of-the-art performance on the common entity prediction task, i.e., giving head (or tail) and relation to predict the tail (or the head), using two benchmark data sets. Furthermore, the deep sequential characteristic of our method enables it to predict the relations given head (or tail) only, and even predict the whole triples. Our experiments on these two new KG completion tasks demonstrate that our method achieves superior performance compared with several alternative methods.
登录
查看更多内容
DOI:
10.1609/aaai.v32i1.11573
发表时间:
2017-07
期刊:
--
影响因子:
--
作者:
Tim Dettmers;Pasquale Minervini;Pontus Stenetorp;S. Riedel
通讯作者:
Tim Dettmers;Pasquale Minervini;Pontus Stenetorp;S. Riedel
DOI:
10.18653/v1/n16-1054
发表时间:
2016-06
期刊:
--
影响因子:
--
作者:
Dat Quoc Nguyen;Kairit Sirts;Lizhen Qu;Mark Johnson
通讯作者:
Dat Quoc Nguyen;Kairit Sirts;Lizhen Qu;Mark Johnson
DOI:
10.1609/aaai.v25i1.7917
发表时间:
2011-08
期刊:
Proceedings of the AAAI Conference on Artificial Intelligence
影响因子:
--
作者:
Antoine Bordes;J. Weston;R. Collobert;Yoshua Bengio
通讯作者:
Antoine Bordes;J. Weston;R. Collobert;Yoshua Bengio
DOI:
10.1609/aaai.v31i1.10952
发表时间:
2016-04
期刊:
ArXiv
影响因子:
--
作者:
Han Xiao;Minlie Huang;Lian Meng;Xiaoyan Zhu
通讯作者:
Han Xiao;Minlie Huang;Lian Meng;Xiaoyan Zhu
DOI:
10.1109/icicip.2013.6568119
发表时间:
2013-06
期刊:
2013 Fourth International Conference on Intelligent Control and Information Processing (ICICIP)
影响因子:
--
作者:
G. Sun;Ce Ding
通讯作者:
G. Sun;Ce Ding