A Unified Approach to Researcher Profiling

Abstract

This paper addresses the issue of researcher profiling. By researcher profiling, we mean building a semantic profile for an academic researcher, by identifying and annotating information from the Web. Previously, person profile annotation was often undertaken separately in an ad-hoc fashion. This paper first gives a formalization of the entire problem and proposes a unified approach to perform the task using Conditional Random Fields (CRF). The paper shows that with introduction of a set of tags, most of the annotation tasks can be performed within this approach. Experiments show that significant improvements over the separated method can be obtained, because the subtasks of annotation are interdependent and should be performed together. The method has been applied to expert finding. Experimental results show that the performance of expert finding can be significantly improved by using the profiling method.