Paper: Uncertainty Detection as Approximate Max-Margin Sequence Labelling

ACL ID W10-3012
Title Uncertainty Detection as Approximate Max-Margin Sequence Labelling
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2010

This paper reports experiments for the CoNLL-2010 shared task on learning to detect hedges and their scope in natu- ral language text. We have addressed the experimental tasks as supervised lin- ear maximum margin prediction prob- lems. For sentence level hedge detection in the biological domain we use an L1- regularisedbinarysupportvectormachine, while for sentence level weasel detection in the Wikipedia domain, we use an L2- regularised approach. We model the in- sentence uncertainty cue and scope de- tection task as an L2-regularised approxi- mate maximum margin sequence labelling problem, using the BIO-encoding. In ad- dition to surface level features, we use a variety of linguistic features based on a functional dependency analysis. A greedy forward selection strategy is used in ex- p...