TY - CHAP

T1 - Hedge Detection Using the RelHunter Approach

AU - Fernandes, Eraldo R.

AU - Crestana, Carlos E. M.

AU - Milidiú, Ruy L.

N1 - Conference code: 14

PY - 2010

Y1 - 2010

N2 - 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 Task. 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 sub-task, 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.

AB - 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 Task. 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 sub-task, 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.

KW - Informatics

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=85123205923&partnerID=8YFLogxK

M3 - Article in conference proceedings

SN - 978-1-932432-84-8

T3 - CoNLL '10: Shared Task

SP - 64

EP - 69

BT - Proceedings of the Fourteenth Conference on Computational Natural Language Learning --- Shared Task

A2 - Farkas, Richard

A2 - Vincze, Veronika

A2 - Szarvas, György

A2 - Mora, György

A2 - Csirik, Janos

PB - Association for Computational Linguistics (ACL)

CY - USA

T2 - 14th Conference on Computational Natural Language Learning - CoNLL 2010

Y2 - 15 July 2010 through 17 July 2010

ER -