Unlexicalised hidden variable models of split dependency grammars
Gabriele Musillo, Paola Merlo · 2008
This paper investigates transforms of split dependency grammars into unlexicalised context-free grammars annotated with hidden symbols. Our best unlexicalised grammar achieves an accuracy of 88% on the Penn Treebank data set, that represents a 50% reduction in error over previously published results on unlexicalised dependency parsing.