Paper: A Cascade Method for Detecting Hedges and their Scope in Natural Language Text

ACL ID W10-3002
Title A Cascade Method for Detecting Hedges and their Scope in Natural Language Text
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2010
Authors

Detecting hedges and their scope in nat- ural language text is very important for information inference. In this paper, we present a system based on a cascade method for the CoNLL-2010 shared task. The system composes of two components: one for detecting hedges and another one for detecting their scope. For detecting hedges, we build a cascade subsystem. Firstly, a conditional random field (CRF) model and a large margin-based model are trained respectively. Then, we train an- other CRF model using the result of the first phase. For detecting the scope of hedges, a CRF model is trained according to the result of the first subtask. The ex- periments show that our system achieves 86.36% F-measure on biological corpus and 55.05% F-measure on Wikipedia cor- pus for hedge detection, and 49.95% F...