Does Universal Dependencies need a parsing representation? An investigation of English

This paper investigates the potential of defining a parsing representation for English data in Universal Dependencies, a crosslingual dependency scheme. We investigate structural transformations that change the choices of headedness in the dependency tree. The transformations make auxiliaries, copulas, subordinating conjunctions and prepositions heads, while in UD they are dependents of a lexical head. We show experimental results for the performance of MaltParser, a data-driven transition-based parser, on the product of each transformation. While some transformed representations favor performance, inverting the transformations to obtain UD for the final product propagates errors, in part due to the nature of lexical-head representations. This prevents the transformations from being profitably used to improve parser performance in that representation.