Large-scale knowledge graphs have currently reached impressive sizes; however, they are still far from complete. In addition, most existing methods for knowledge graph completion only consider the direct links between entities, ignoring the vital impact of the semantics of relation paths. In this paper, we study the problem of how to better embed entities and relations of knowledge graphs into different low-dimensional spaces by taking full advantage of the additional semantics of relation paths and propose a novel relation path embedding model named as RPE. Specifically, with the corresponding relation and path projections, RPE can simultaneously embed each entity into two types of latent spaces. Moreover, type constraints are extended from traditional relation-specific type constraints to the proposed path-specific type constraints and both of the two type constraints can be seamlessly incorporated into RPE. The proposed model is evaluated on the benchmark tasks of link prediction and triple classification. The results of experiments demonstrate our method outper- forms all baselines on both tasks. They indicate that our model is capable of catching the semantics of relation paths, which is significant for knowledge representation learning.

Relation path embedding in knowledge graphs / Lin, Xixun; Liang, Yanchun; Giunchiglia, Fausto; Feng, Xiaoyue; Guan, Renchu. - In: NEURAL COMPUTING & APPLICATIONS. - ISSN 1433-3058. - ELETTRONICO. - 31:(2018), pp. 5629-5639. [10.1007/s00521-018-3384-6]

Relation path embedding in knowledge graphs

Yanchun Liang;Fausto Giunchiglia;
2018

Abstract

Large-scale knowledge graphs have currently reached impressive sizes; however, they are still far from complete. In addition, most existing methods for knowledge graph completion only consider the direct links between entities, ignoring the vital impact of the semantics of relation paths. In this paper, we study the problem of how to better embed entities and relations of knowledge graphs into different low-dimensional spaces by taking full advantage of the additional semantics of relation paths and propose a novel relation path embedding model named as RPE. Specifically, with the corresponding relation and path projections, RPE can simultaneously embed each entity into two types of latent spaces. Moreover, type constraints are extended from traditional relation-specific type constraints to the proposed path-specific type constraints and both of the two type constraints can be seamlessly incorporated into RPE. The proposed model is evaluated on the benchmark tasks of link prediction and triple classification. The results of experiments demonstrate our method outper- forms all baselines on both tasks. They indicate that our model is capable of catching the semantics of relation paths, which is significant for knowledge representation learning.
Lin, Xixun; Liang, Yanchun; Giunchiglia, Fausto; Feng, Xiaoyue; Guan, Renchu
Relation path embedding in knowledge graphs / Lin, Xixun; Liang, Yanchun; Giunchiglia, Fausto; Feng, Xiaoyue; Guan, Renchu. - In: NEURAL COMPUTING & APPLICATIONS. - ISSN 1433-3058. - ELETTRONICO. - 31:(2018), pp. 5629-5639. [10.1007/s00521-018-3384-6]
File in questo prodotto:
File Dimensione Formato  
Relation path embedding in knowledge graphs.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 1.59 MB
Formato Adobe PDF
1.59 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11572/202602
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 12
social impact