Relation Extraction for Mining the Semantic Web

The knowledge acquisition bottleneck problem, well-known to the Knowledge Management community, is turning the weaving of the Semantic Web (SW) into a hard and slow process. Nowadays' high costs associated with producing two versions of a document – one version for human consumption and another version for machine consumption – prevent the creation of enough metadata to make the SW realizable. There are several potential solutions to the problem. We advocate the use of automated methods for semantic markup, i.e., for mapping parts of unstructured text into a structured representation such as ontology. In this paper, we describe initial work on a general software framework for supervised extraction of entities and relations from text. The framework was designed so as to provide the degree of flexibility required by automatic semantic markup tasks for the Semantic Web.