On the Representation and Embedding of Knowledge Bases beyond Binary Relations

Wen, Jianfeng; Li, Jianxin; Mao, Yongyi; Chen, Shini; Zhang, Richong

On the Representation and Embedding of Knowledge Bases beyond Binary Relations

Jianfeng Wen, Jianxin Li, Yongyi Mao, Shini Chen, Richong Zhang

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 1300-1306.

Abstract

The models developed to date for knowledge base embedding are all based on the assumption that the relations contained in knowledge bases are binary.For the training and testing of these embedding models, multi-fold (or n-ary) relational data are converted to triples (e.g., in FB15K dataset)and interpreted as instances of binary relations.This paper presents a canonical representation of knowledge bases containing multi-fold relations.We show that the existing embedding models on the popular FB15K datasets correspond to a suboptimal modelling framework, resulting in a loss of structural information. We advocate a novel modelling framework, which models multi-fold relations directly using this canonical representation.Using this framework, the existing TransH model is generalized to a new model, m-TransH. We demonstrate experimentally that m-TransH outperforms TransH by a large margin, thereby establishing a new state of the art.

Jianfeng Wen, Jianxin Li, Yongyi Mao, Shini Chen, and Richong Zhang. 2016. On the Representation and Embedding of Knowledge Bases beyond Binary Relations. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 1300–1306. https://ijcai.org/proceedings/2016/188

@inproceedings{ijcai2016p188,
  title     = {On the Representation and Embedding of Knowledge Bases beyond Binary Relations},
  author    = {Wen, Jianfeng and Li, Jianxin and Mao, Yongyi and Chen, Shini and Zhang, Richong},
  booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-16}},
  publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
  editor    = {Subbarao Kambhampati},
  pages     = {1300--1306},
  year      = {2016},
  month     = {7},
  url       = {https://ijcai.org/proceedings/2016/188},
}

TY  - CPAPER
TI  - On the Representation and Embedding of Knowledge Bases beyond Binary Relations
AU  - Wen, Jianfeng
AU  - Li, Jianxin
AU  - Mao, Yongyi
AU  - Chen, Shini
AU  - Zhang, Richong
T2  - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16
PB  - AAAI Press / International Joint Conferences on Artificial Intelligence
PY  - 2016
SP  - 1300
EP  - 1306
UR  - https://ijcai.org/proceedings/2016/188
ER  -