Paper: HedgeHunter: A System for Hedge Detection and Uncertainty Classification

ACL ID W10-3017
Title HedgeHunter: A System for Hedge Detection and Uncertainty Classification
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2010
Authors

With the dramatic growth of scientific publishing, Information Extraction (IE) systems are becoming an increasingly im- portant tool for large scale data analy- sis. Hedge detection and uncertainty clas- sification are important components of a high precision IE system. This paper describes a two part supervised system which classifies words as hedge or non- hedged and sentences as certain or uncer- tain in biomedical and Wikipedia data. In the first stage, our system trains a logistic regressionclassifiertodetecthedgesbased on lexical and Part-of-Speech collocation features. In the second stage, we use the output of the hedge classifier to generate sentence level features based on the num- ber of hedge cues, the identity of hedge cues, and a Bag-of-Words feature vector to train a logistic...