Presentation 2019-06-01
Jointly Embedding Knowledge Graph and Feature in Vector Space
Tomu Kadoki, Runhe Huang, Satoru Fujita,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Knowledge Graph, utilized in search engine, can be embed in a low dimensional vector space with knowledge graph embedding model. The traditional approach for knowledge graph embedding model could hardly express overloading meaning in entities. In this paper, we propose WKmodel that embeds similarity in the word representation in vector space into the knowledge graph embedding model. We compared WKmodel with TransE in terms of the performance of knowledge graph and similarities between the embedding model and the word representation in vector space. There are two results shown in this paper; WKmodel can embed similarity of word representation in the vector space with knowledge, and achieves the balanced performance in entity prediction by embedding the similarity measure from knowledge.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Knowledge graph / Knowledge embedding model / Word vector / Entity prediction / Word similarity
Paper # SC2019-10
Date of Issue 2019-05-24 (SC)

Conference Information
Committee SC
Conference Date 2019/5/31(2days)
Place (in Japanese) (See Japanese page)
Place (in English) National Institute for Materials Science
Topics (in Japanese) (See Japanese page)
Topics (in English) Science Service Platform, Data Service and Machine Learning, etc
Chair Masahide Nakamura(Kobe Univ.)
Vice Chair Shinji Kikuchi(National Institute for Materials Science) / Yoji Yamato(NTT)
Secretary Shinji Kikuchi(Tokyo University of Technology) / Yoji Yamato(Fujitsu Lab.)

Paper Information
Registration To Technical Committee on Service Computing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Jointly Embedding Knowledge Graph and Feature in Vector Space
Sub Title (in English)
Keyword(1) Knowledge graph
Keyword(2) Knowledge embedding model
Keyword(3) Word vector
Keyword(4) Entity prediction
Keyword(5) Word similarity
1st Author's Name Tomu Kadoki
1st Author's Affiliation Hosei University(Hosei Univ.)
2nd Author's Name Runhe Huang
2nd Author's Affiliation Hosei University(Hosei Univ.)
3rd Author's Name Satoru Fujita
3rd Author's Affiliation Hosei University(Hosei Univ.)
Date 2019-06-01
Paper # SC2019-10
Volume (vol) vol.119
Number (no) SC-66
Page pp.pp.55-60(SC),
#Pages 6
Date of Issue 2019-05-24 (SC)