Paper: On Reverse Feature Engineering of Syntactic Tree Kernels

ACL ID W10-2926
Title On Reverse Feature Engineering of Syntactic Tree Kernels
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2010
Authors

In this paper, we provide a theoretical framework for feature selection in tree ker- nel spaces based on gradient-vector com- ponents of kernel-based machines. We show that a huge number of features can be discarded without a significant decrease in accuracy. Our selection algorithm is as accurate as and much more efficient than those proposed in previous work. Com- parative experiments on three interesting and very diverse classification tasks, i.e. Question Classification, Relation Extrac- tion and Semantic Role Labeling, support our theoretical findings and demonstrate the algorithm performance.