Risk event and probability extraction for modeling medical risks

Abstract

In this paper we address the task of extracting risk events and probabilities from free text, focusing in particular on the biomedical domain. While our initial motivation is to ena ble the determination of the parameters of a Bayesian bel ief network, our approach is not specific to that use case. We arc the first to investigate this task as a sequence tagg ing problem where we label spans of text as events A or B that are then used to construct probability statements of the form P(AB) = x. We show that our approach significantly outperforms an entity extraction baseline on a new annotated medical risk event corpus. We also explore semi-supervised methods that lead to modest improvement, encouraging furt her work in this direction.