Getting the Most out of Transition-based Dependency Parsing

Jinho D. Choi1 and Martha Palmer2
1University of Colorado at Boulder, 2Getting the Most out of Transition-based Dependency Parsing


Abstract

This paper suggests two ways of improving transition-based, non-projective dependency parsing. First, we add a transition to an existing non-projective parsing algorithm, so it can perform either projective or non-projective parsing as needed. Second, we introduce a bootstrapping technique to narrow down discrepancies between gold-standard and automatic parses that are used as features. The new addition to the algorithm shows a clear advantage in parsing speed. The bootstrapping technique gives a significant improvement to parsing accuracy, showing near state-of-the-art performance with respect to other parsing approaches evaluated on the same data.




Full paper: http://www.aclweb.org/anthology/P/P11/P11-2121.pdf