Paper: Hedge Detection and Scope Finding by Sequence Labeling with Procedural Feature Selection

ACL ID W10-3013
Title Hedge Detection and Scope Finding by Sequence Labeling with Procedural Feature Selection
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2010
Authors

This paper presents a system which adopts a standard sequence labeling technique for hedge detection and scope finding. For the first task, hedge detection, we formu- late it as a hedge labeling problem, while for the second task, we use a two-step la- beling strategy, one for hedge cue label- ing and the other for scope finding. In par- ticular, various kinds of syntactic features are systemically exploited and effectively integrated using a large-scale normalized feature selection method. Evaluation on the CoNLL-2010 shared task shows that our system achieves stable and competi- tive results for all the closed tasks. Fur- thermore, post-deadline experiments show that the performance can be much further improved using a sufficient feature selec- tion.