Poster – Paper 617
Yohei Onuki, Tsuyoshi Murata, Shun Nukui, Seiya Inagi, Xule Qiu, Masao Watanabe and Hiroshi OkamotoPoster
October 23, 2017, Poster and Demo Reception, 18:30-21:20
Download paper (preprint)
The goal of our research is to predict a relation (predicate) of two given RDF entities (subject and object). Link prediction between entities is important for developing large-scale ontologies and for knowledge graph completion. TransE and TransR have been proposed as the methods for such a prediction. However, TransE and TransR embed both entities and relations in the same (or different) semantic space(s). Since entity embedding is enough for predicting relations, we propose a method for predicting a predicate from a subject and an object by using a Deep Neural Network (DNN), and developed RDFDNN. RDFDNN embeds
entities only; given subject and object are embedded and concatenated to predict probability distribution of predicates. Experimental results showed that predictions by RDFDNN are more accurate than those by TransE and TransR. Although RDFDNN learns from RDF triples only, its accuracy is comparable to that of DKRL which uses both RDF triples and entity descriptions for learning.