MeDetect: Domain entity annotation in biomedical references using linked open data

Abstract

Recently, with the ever-growing use of textual medicine records, annotating domain entities has been regarded as an important task in the biomedical field. On the other hand, the process of interlinking open data sources is being actively pursued within the Linking Open Data (LOD) project. The number of entities and the number of properties describing semantic relationships between entities within the linked data cloud are very large. In this paper, we propose a knowledge-incentive approach based on LOD for entity annotation in the biomedical field. With this approach, we implement MeDetect, a prototype system to solve the problems mentioned above. The experimental results verify the effectiveness and efficiency of our approach.