Integration of Static Relations to Enhance Event Extraction from Text

As research on biomedical text mining is shifting focus from simple binary relations to more expressive event representations, extraction performance drops due to the increase in complexity. Recently introduced data sets specifically targeting static relations between named entities and domain terms have been suggested to enable a better representation of the biological processes underlying annotated events and opportunities for addressing their complexity. In this paper, we present the first study of integrating these static relations with event data with the aim of enhancing event extraction performance. While obtaining promising results, we will argue that an event extraction framework will benefit most from this new data when taking intrinsic differences between various event types into account.