A study on measurement of similarity for interlinking chinese, japanese and korean resources

Abstract

Linked Open Data (LOD) is an international endeavor to interlink structured data on the Web and create the Web of Data on a global level. Linking data can be achieved by understanding semantic relationships between data and building explicit links for them. One serious challenge that deters this worldwide initiative is the issue of multilinguality. The current LOD provides limited support for non-Western data, in particular for Asian data. In this study, we propose a novel method with which Chinese, Japanese, and Korean (CJK) resources can be better matched and connected. The three countries share Chinese characters even though Japan and Korea have their own language. Utilizing the Unihan database, which covers more than 45,000 characters commonly used for the three countries, we show that the proposed method outperforms the traditional method based on string matching in finding similar characters and words among the three countries. The results represent the first step towards overcoming the multilingual barrier in semantically interlinking LOD resources across the three countries.