Detecting uncertainty in biomedical literature: a simple disambiguation approach using sparse random indexing

This paper presents a novel approach to the problem of hedge detection, which involves the identification of so-called hedge cues for labeling sentences as certain or uncertain. This is the classification problem for Task 1 of the CoNLL-2010 Shared Task, which focuses on hedging in biomedical literature. We here propose to view hedge detection as a simple disambiguation problem, restricted to words that have previously been observed as hedge cues. Applying an SVM classifier, the approach achieves the best published results so far for sentence-level uncertainty prediction on the Shared Task test data. We also show that the technique of random indexing can be successfully applied for compressing the dimensionality of the original feature space by several orders of magnitude, while at the same time yielding better classifier performance.