Paper: Automatic Discovery of Feature Sets for Dependency Parsing

ACL ID C10-1093
Title Automatic Discovery of Feature Sets for Dependency Parsing
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2010

This paper describes a search procedure to discover optimal feature sets for depen- dency parsers. The search applies to the shift–reduce algorithm and the feature sets are extracted from the parser configura- tion. The initial feature is limited to the first word in the input queue. Then, the procedure uses a set of rules founded on the assumption that topological neighbors of significant features in the dependency graph may also have a significant contri- bution. The search can be fully automated and the level of greediness adjusted with the number of features examined at each iteration of the discovery procedure. Using our automated feature discovery on two corpora, the Swedish corpus in CoNLL-X and the English corpus in CoNLL 2008, and a single parser system, we could reach results c...