Paper: Getting the Most out of Transition-based Dependency Parsing

ACL ID P11-2121
Title Getting the Most out of Transition-based Dependency Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

This paper suggests two ways of improving transition-based, non-projective dependency parsing. First, we add a transition to an exist- ing non-projective parsing algorithm, so it can perform either projective or non-projective parsing as needed. Second, we present a boot- strapping technique that narrows down dis- crepancies between gold-standard and auto- matic parses used as features. The new ad- dition to the algorithm shows a clear advan- tage 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 set.