DCU-Paris13 systems for the SANCL 2012 shared task

Abstract

The DCU-Paris13 team submitted three systems to the SANCL 2012 shared task on parsing English web text. The first submission, the highest ranked constituency parsing system, uses a combination of PCFG-LA product grammar parsing and self-training. In the second submission, also a constituency parsing system, the n-best lists of various parsing models are combined using an approximate sentence-level product model. The third system, the highest ranked system in the dependency parsing track, uses voting over dependency arcs to combine the output of three constituency parsing systems which have been converted to dependency trees. All systems make use of a data-normalisation component, a parser accuracy predictor and a genre classifier.