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。
Abstract
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.
关键词
知识库 /
深度学习 /
三元组分类
{{custom_keyword}} /
Key words
knowledge base /
deep learning /
triple classification
/
/
/
/
/
/
/
/
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] R Socher, D Chen, C D Manning, et al. Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of the Advances in Neural Information Processing Systems,2013:926-934.
[2] A Bordes, N Usunier, A Garcia-Duran, et al. Translating embeddings for modeling multi-relational data[C]//Proceedings of the Advances in Neural Information Processing Systems,2013:2787-2795.
[3] Miao Fan, Qiang Zhou, Emily Chang, et al. Transition-based Knowledge graph embedding with relation mapping properties[C]//Proceedings of the PACLIC,2014:328-337.
[4] Bordes A,Glorot X, Weston J, et al. A semantic matching energy function for learning with multirelational data[J]. Machine Learning,2014,(2):1-27.
[5] A Bordes, J Weston, R Collobert, et al. Learning structured embeddings of knowledge bases[C]//Proceedings of the AAAI,2011:201-306.
[6] I Sutskever, R Salakhutdinov, J B Tenenbaum. Modelling relational data using bayesian clustered tensor factorization[C]//Proceedings of the NIPS,2009:1821-1828.
[7] Wang Z, Zhang J, Feng J, et al. Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of AAAI,2014:1112-1119.
[8] Yankai Lin, Zhiyuan Liu, Maosong Sun, et al. Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the AAAI,2015:2181-2187.
[9] Miao Fan, Kai Cao, Yifan He. Jointly Embedding Relations and Mentions for Knowledge Population[J]. arXiv preprint,2015:arXiv:1504.01683.[10] Socher R, Chen D, Manning C D, et al. Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of NIPS,2013:926-934.
[11] Bengio Y, Ducharme R, Vincent P, et al. A neural probabilistic language model[J]. JMLR,2003, 3:1137-1155.
[12] Jenatton R, Roux N L, Bordes A, et al. A latent factor model for highly multi-relational data[C]//Proceedings of NIPS,2012:3167-3175.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61540057,61433015,61272324,61572477);青海省自然科学基金(2016-ZJ-Y04,2016-ZJ-740)
{{custom_fund}}
PDF(618 KB)
