Combining topic model and co-author network for KAKEN and DBLP linking

Authors:
Duy-Hoang Tran;Hideaki Takeda;Kei Kurakawa;Minh-Triet Tran
Affiliations:
Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam;National Institute of Informatics, Japan;National Institute of Informatics, Japan;Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam
Venue:
ACIIDS'12 Proceedings of the 4th Asian conference on Intelligent Information and Database Systems - Volume Part III
Year:
2012

Citing 4
Cited 0

Latent dirichlet allocation

The Journal of Machine Learning Research
The author-topic model for authors and documents

UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Linked data on the web (LDOW2008)

Proceedings of the 17th international conference on World Wide Web
Managing the quality of person names in DBLP

ECDL'06 Proceedings of the 10th European conference on Research and Advanced Technology for Digital Libraries

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Web of Data is based on two simple ideas: to employ the RDF data model to public structured data on the Web and to set explicit RDF links to interlink data items within different data sources. In this paper, we describe our experience in building a system of link discovery between KAKEN, a database provides the latest information of research projects in Japan, and the DBLP Computer Science Bibliography. Using these links one can navigate from the information of a computer scientist in KAKEN to his publications in the DBLP database. Our problem of linkage between KAKE researchers and DBLP authors is name disambiguation. We proposed combining LDA based topic model and co-author network approach to improve linkage accuracy.