Bridging the Gap between Domain-Oriented and Linguistically-Oriented Semantics

This paper compares domain-oriented and linguistically-oriented semantics, based on the GENIA event corpus and FrameNet. While the domain-oriented semantic structures are direct targets of Text Mining (TM), their extraction from text is not straghtforward due to the diversity of linguistic expressions. The extraction of linguistically-oriented semactics is more straghtforward, and has been studied independentely of specific domains. In order to find a use of the domain-independent research achievements for TM, we aim at linking classes of the two types of semantics. The classes were connected by analyzing linguistically-oriented semantics of the expressions that mention one biological class. With the obtained relationship between the classes, we discuss a link between TM and linguistically-oriented semantics.