数据集Freebase-FB13

数据集:

FB13是Freebase的子集,包含13种关系和75k种实体。
https://download.csdn.net/download/qq_21097885/11013054

类别数量
#Relation13
#Entity75,043
#Train316,232
#Valid5,908
#Test23,733

相关论文:

  • TransE: Translating Embeddings for Modeling Multi-relational Data
  • TransH: Knowledge Graph Embedding by Translating on Hyperplanes
  • TransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion
  • TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix
  • KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding

实验结果:

modelunifbern
TransE [1]70.981.5
TransH [2]76.583.3
TransR [3]74.782.5
TransD [4]85.989.1
KG2E [5]76.485.3

参考文献:

[1] Bordes, A., et al., Translating Embeddings for Modeling Multi-relational Data, in Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States. 2013. p. 2787-2795.

[2] Wang, Z., et al., Knowledge Graph Embedding by Translating on Hyperplanes, in Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, July 27 -31, 2014, Québec City, Québec, Canada. 2014. p. 1112-1119.

[3] Lin, Y., et al., Learning Entity and Relation Embeddings for Knowledge Graph Completion, in Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, January 25-30, 2015, Austin, Texas, USA. 2015. p. 2181-2187.

[4] Ji, G., et al., Knowledge Graph Embedding via Dynamic Mapping Matrix, in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL 2015, July 26-31, 2015, Beijing, China, Volume 1: Long Papers. 2015. p. 687-696.

[5] He, S., et al., Learning to Represent Knowledge Graphs with Gaussian Embedding, in Proceedings of the 24th ACM International Conference on Information and Knowledge Management, CIKM 2015, Melbourne, VIC, Australia, October 19 - 23, 2015. 2015. p. 623-632.

  • 0
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值