数据集Freebase-FB15k-237

数据集：

FB15k-237是Freebase的子集，包含237种关系和14k种实体。
https://download.csdn.net/download/qq_21097885/12340908

类别	数量
#Relation	237
#Entity	14,541
#Train	271,115
#Valid	17,535
#Test	20,466

相关论文：

CP: The expression of a tensor or a polyadic as a sum of products
DistMult: Embedding Entities and Relations for Learning and Inference in Knowledge Bases
ComplEx: Complex Embeddings for Simple Link Prediction
HolE: Holographic Embeddings of Knowledge Graphs
TransE: Translating Embeddings for Modeling Multi-relational Data
R-GCN: Modeling Relational Data with Graph Convolutional Networks
ConvE: Convolutional 2D Knowledge Graph Embeddings

实验结果：

model	Raw MRR	Filter MRR	Filter Hits@1	Filter Hits@3	Filter Hits@10
CP [1]	0.080	0.182	0.101	0.197	0.357
DistMult [2]	0.100	0.191	0.106	0.207	0.376
ComplEx [3]	0.109	0.201	0.112	0.213	0.388
HolE [4]	0.124	0.222	0.133	0.253	0.391
TransE [5]	0.144	0.233	0.147	0.263	0.398
R-GCN [6]	0.158	0.248	0.153	0.258	0.414
ConvE [7]	-	0.316	0.239	0.350	0.491

参考文献：

[1] Hitchcock, F.L., The expression of a tensor or a polyadic as a sum of products, in Studies in Applied Mathematics 6, 1-4. 1927. p. 164–189.

[2] Yang, B., et al., Embedding Entities and Relations for Learning and Inference in Knowledge Bases, 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.

[3] Trouillon, T., et al., Complex Embeddings for Simple Link Prediction, in Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016. 2016. p. 2071-2080.

[4] Nickel, M., L. Rosasco and T.A. Poggio, Holographic Embeddings of Knowledge Graphs, in Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 12-17, 2016, Phoenix, Arizona, USA. 2016. p. 1955-1961.

[5] 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.

[6] Schlichtkrull, M.S., et al., Modeling Relational Data with Graph Convolutional Networks, in The Semantic Web - 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3-7, 2018, Proceedings. 2018. p. 593-607.

[7] Dettmers, T., et al., Convolutional 2D Knowledge Graph Embeddings, in Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018. 2018. p. 1811-1818.

数据集Freebase-FB15k-237相关推荐

关于对KB4Rec数据集的学习
1.数据集的组成此数据集是将一些其他的数据集联系起来之后得到的一个数据集. 其他的数据集分为两类,分别是推荐系统的数据集和知识库.推荐系统的数据集(RS data sets),包括MovieLens ...
Transformer BERT KG-BERT
两个重要的知识表示学习综述: 知乎: 1. KG笔记十.知识图谱嵌入(KG Embedding)https://zhuanlan.zhihu.com/p/354867179 2. 刘知远大神<知 ...
半小时训练亿级规模知识图谱，亚马逊AI开源知识图谱嵌入表示框架DGL-KE
出品 | AI科技大本营(ID:rgznai100) 知识图谱 (Knowledge Graph)作为一个重要的技术,在近几年里被广泛运用在了信息检索,自然语言处理,以及推荐系统等各种领域.学习知识图 ...
半小时训练亿级规模知识图谱，亚马逊AI开源知识图谱嵌入表示框架
来源:AI 科技大本营本文约2300字,建议阅读9分钟亚马逊 AI 团队开源了一款专门针对大规模知识图谱嵌入表示的新训练框架 DGL-KE,能让研究人员和工业界用户方便.快速地在大规模知识图谱数据 ...
半小时训练亿级规模知识图谱，亚马逊这个 AI 框架要火
2020-04-08 20:08:14 出品 | AI科技大本营(ID:rgznai100) 知识图谱 (Knowledge Graph)作为一个重要的技术,在近几年里被广泛运用在了信息检索,自然语言 ...
技术实践：大规模知识图谱预训练及电商应用
本文作者: 张文(浙江大学).黄志文(阿里巴巴).叶橄强(浙江大学).文博(浙江大学).张伟(阿里巴巴),陈华钧*(浙江大学) 接收会议: ICDE 2021 1. 文章导读本文介绍了浙江大学阿里巴 ...
技术实践 | ICDE2021-大规模知识图谱预训练及电商应用
本文作者 | 张文(浙江大学).黄志文(阿里巴巴).叶橄强(浙江大学).文博(浙江大学).张伟(阿里巴巴),陈华钧*(浙江大学) 接收会议 | ICDE2021 转载公众号 | ZJUKG (欢迎转载 ...
论文浅尝 - ACL2020 | Segmented Embedding of Knowledge Graphs
来源:ACL2020 链接:https://arxiv.org/pdf/2005.00856.pdf 摘要知识图谱的嵌入愈发变成AI的热点之一,对许多下游任务至关重要(如个性化推荐.问答等) 同时, ...
论文浅尝 | AAAI2020 - 基于规则的知识图谱组合表征学习
论文笔记整理:康矫健,浙江大学计算机科学与技术系,硕士研究生. 论文链接:https://arxiv.org/pdf/1911.08935.pdf 发表会议:AAAI 2020 Motivation ...
论文浅尝 | 基于知识库的自然语言理解 03#
本文转载自公众号: 知识工场. 罗康琦,上海交通大学计算机系2019届博士,研究方向为自然语义理解和知识图谱.2012年获得华中科技大学软件工程学士学位,现就职于京东数据科学实验室(Data Scie ...

数据集Freebase-FB15k-237

数据集Freebase-FB15k-237相关推荐

最新文章

热门文章