Construction of a Japanese gazetteers for Japanese local toponym disambiguation

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.