Hedge Detection Using the RelHunter Approach

RelHunter is a Machine Learning based method for the extraction of structured information from text. Here, we apply RelHunter to the Hedge Detection task, proposed as the CoNLL-2010 Shared Task1. RelHunter’s key design idea is to model the target structures as a relation over entities. The method decomposes the original task into three subtasks: (i) Entity Identification; (ii) Candidate Relation Generation; 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 decomposed into three token classification subtasks, one for each entity type. In the Candidate Relation Generation subtask, we apply a simple procedure to generate a ternary candidate relation. Each instance in this relation represents a hedge candidate composed by a cue chunk, a start scope token and an end scope token. For the Relation Recognition subtask, we use a binary classifier to discriminate between true and false candidates. The four classifiers are trained with the Entropy Guided Transformation Learning algorithm. When compared to the other hedge detection systems of the CoNLL shared task, our scheme shows a competitive performance. The F -score of our system is 54.05 on the evaluation corpus. ∗ This work is partially funded by CNPq and FAPERJ grants 557.128/2009-9 and E-26/170028/2008. † Holds a CNPq doctoral fellowship and has financial support from IFG, Brazil. ‡Holds a CAPES doctoral fellowship. §Holds a CNPq research fellowship. Closed Task 2: detection of hedge cues and their scopes.