Construction of a Japanese gazetteers for Japanese local toponym disambiguation

Authors:
Masaharu Yoshioka;Takahiro Fujiwara
Affiliations:
Hokkaido University, Hokkaido, Japan;Hokkaido University, Hokkaido, Japan
Venue:
Proceedings of the 7th Workshop on Geographic Information Retrieval
Year:
2013

Citing 9
Cited 0

Japanese dependency analysis using cascaded chunking

COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
A confidence-based framework for disambiguating geographic terms

HLT-NAACL-GEOREF '03 Proceedings of the HLT-NAACL 2003 workshop on Analysis of geographic references - Volume 1
Mining a Multilingual Geographical Gazetteer from the Web

WI-IAT '09 Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology - Volume 01
Approaches to disambiguating toponyms

SIGSPATIAL Special
Fast track article: Looking ahead in pervasive computing: Challenges and opportunities in the era of cyber-physical convergence

Pervasive and Mobile Computing
Fast track article: Looking ahead in pervasive computing: Challenges and opportunities in the era of cyber-physical convergence

Pervasive and Mobile Computing
GeoWordNet: a resource for geo-spatial applications

ESWC'10 Proceedings of the 7th international conference on The Semantic Web: research and Applications - Volume Part I
YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia

Artificial Intelligence
An algorithm for local geoparsing of microtext

Geoinformatica

Quantified Score

Hi-index	0.00

Visualization

Abstract

When processing toponym information in natural language text, it is crucial to have a good gazetteers. There are several well-organized gazetteers for English text, but they do not cover Japanese local toponyms. In this paper, we introduce a Japanese gazetteers based on Open Data (e.g., the Toponym database distributed by Japanese ministries, Wikipedia, and GeoNames) and propose a toponym disambiguation framework that uses the constructed gazetteers. We also evaluate our approach based on a blog corpus that contains place names with high ambiguity.