Exploring Automatic Feature Selection for Transition-Based Dependency Parsing

Miguel Ballesteros


In this paper we investigate automatic techniques for finding an optimal feature model in the case of transition-based dependency parsing. We show a comparative study making a distinction between search algorithms, validation and decision rules demonstrating at the same time that using our methods it is possible to come up with quite complex feature specifications which are able to provide better results than default feature models.

Texto completo: