Paper: Hedge Detection Using the RelHunter Approach

ACL ID W10-3009
Title Hedge Detection Using the RelHunter Approach
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2010

RelHunter is a Machine Learning based method for the extraction of structured in- formation from text. Here, we apply Rel- Hunter to the Hedge Detection task, pro- posed as the CoNLL-2010 Shared Task1. RelHunter’s key design idea is to model the target structures as a relation over enti- ties. The method decomposes the original task into three subtasks: (i) Entity Iden- tification; (ii) Candidate Relation Gener- ation; and (iii) Relation Recognition. In the Hedge Detection task, we define three types of entities: cue chunk, start scope token and end scope token. Hence, the Entity Identification subtask is further de- composed into three token classification subtasks, one for each entity type. In the Candidate Relation Generation sub- task, we apply a simple procedure to gen- erate a tern...