Exploiting background knowledge for relation extraction

Abstract

Relation extraction is the task of recognizing semantic relations among entities. Given a particular sentence supervised approaches to Relation Extraction employed feature or kernel functions which usually have a single sentence in their scope. The overall aim of this paper is to propose methods for using knowledge and resources that are external to the target sentence, as a way to improve relation extraction. We demonstrate this by exploiting background knowledge such as relationships among the target relations, as well as by considering how target relations relate to some existing knowledge resources. Our methods are general and we suggest that some of them could be applied to other NLP tasks.