Václav Klimes

Learn More
This paper gives an overview of the current state of the Prague English Dependency Tree-bank project. It is an updated version of a draft text that was released along with a CD presenting the first 25% of the PDT-like version of the Penn Treebank – WSJ section (PEDT 1.0). Before the January 2009 release, the conversion from the original phrase structure(More)
This paper introduces two methods of dependency parsing by means of rules automatically inferred from training data. For Czech the accuracy of the proposed parsers is considerably behind that of the state-of-the-art parsers, but the paper brings a new method of inference of rules and applies transformation-based learning to parsing in a novel way. Moreover,(More)
  • 1