Knowledge base completion by learning pairwise-interaction differentiated embeddings
Knowledge base completion by learning pairwise-interaction differentiated embeddings
复制标题
通过学习成对交互差异化嵌入完成知识库
DOI:
10.1007/s10618-015-0430-1
复制
发表时间:
2015-09
影响因子:
4.8
通讯作者:
Jun Guo
中科院分区:
文献类型:
--
作者:
Yu Zhao;Sheng Gao;Patrick Gallinari;Jun Guo
A knowledge base of triples like(subject entity, predicate relation,object entity)is a very important resource for knowledge management. It is very useful for human-like reasoning, query expansion, question answering (Siri) and other related AI tasks. However, such a knowledge base often suffers from incompleteness due to a large volume of increasing knowledge in the real world and a lack of reasoning capability. In this paper, we propose a Pairwise-interaction Differentiated Embeddings model to embed entities and relations in the knowledge base to low dimensional vector representations and then predict the possible truth of additional facts to extend the knowledge base. In addition, we present a probability-based objective function to improve the model optimization. Finally, we evaluate the model by considering the problem of computing how likely the additional triple is true for the task of knowledge base completion. Experiments onWordNetandFreebaseshow the excellent performance of our model and algorithm.
登录
查看更多内容
DOI:
--
发表时间:
2012-07
期刊:
--
影响因子:
--
作者:
E. Huang;R. Socher;Christopher D. Manning;A. Ng
通讯作者:
E. Huang;R. Socher;Christopher D. Manning;A. Ng
DOI:
10.3115/1073083.1073102
发表时间:
2002-07
期刊:
--
影响因子:
--
作者:
Vincent Ng;Claire Gardent
通讯作者:
Vincent Ng;Claire Gardent
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:
--
发表时间:
2009-12
期刊:
--
影响因子:
--
作者:
I. Sutskever;R. Salakhutdinov;J. Tenenbaum
通讯作者:
I. Sutskever;R. Salakhutdinov;J. Tenenbaum
影响因子:
--
作者:
R. Snow;Dan Jurafsky;A. Ng
通讯作者:
R. Snow;Dan Jurafsky;A. Ng