期刊论文、会议论文

Wang, Qi

英文

Lecture Notes in Computer Science

0302-9743

2018

10772

276-288

40th European Conference on Information Retrieval Research (ECIR)

Lecture Notes in Computer Science

MAR 26-29, 2018

Grenoble, FRANCE

[Zhang, Maoyuan;Wang, Qi;Li, Wei;Sun, Shuyuan] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.^[Xu, Wukui] Huazhong Univ Sci & Technol, Intelligent & Distributed Comp Lab, Wuhan, Hubei, Peoples R China.

Lab Informatique Grenoble, British Comp Soc, Informat Retrieval Specialist Grp, Naver Labs, Google, Univ Grenoble Alpes, Grenoble INP, Grenoble Alpes Data Inst, Grenoble Alpes Metropole, Labex, ARIA, ACM Special Interest Grp Informat Retrieval, Springer, Persyval Lab

Pasi, G Piwowarski, B Azzopardi, L Hanbury, A

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

978-3-319-76941-7; 978-3-319-76940-0

10.1007/978-3-319-76941-7_21

Humanity and Social Science Youth Foundation of Ministry of Education of China [15YJC870029]; Research Planning Project of National Language Committee [YB135-40]

本校为第一且通讯机构

Representation learning of knowledge graph aims to transform both the entities and relations into continuous low-dimensional vector space. Though there have been a variety of models for knowledge graph embedding, most existing latent-based models merely explain triples via latent features, while supplementary rich inference patterns hidden in the observed graph features have not been fully employed. For this reason, in this paper we propose the discriminative path-based embedding model (DPTransE) which jointly learns from the latent features and graph features. Our model builds interactions be...