Paper: Dependency Parsing with Second-Order Feature Maps and Annotated Semantic Information

ACL ID W07-2217
Title Dependency Parsing with Second-Order Feature Maps and Annotated Semantic Information
Venue Conference on Parsing Technologies
Session Main Conference
Year 2007
Authors

This paper investigates new design options for the feature space of a dependency parser. We focus on one of the simplest and most efficient architectures, based on a determin- istic shift-reduce algorithm, trained with the perceptron. By adopting second-order fea- ture maps, the primal form of the perceptron produces models with comparable accuracy to more complex architectures, with no need for approximations. Further gains in accu- racy are obtained by designing features for parsing extracted from semantic annotations generated by a tagger. We provide experi- mental evaluations on the Penn Treebank.