Arc-swift: A Novel Transition System for Dependency Parsing

05/12/2017

∙

by   Peng Qi, et al.

∙

0

∙

share

Transition-based dependency parsers often need sequences of local shift and reduce operations to produce certain attachments. Correct individual decisions hence require global information about the sentence context and mistakes cause error propagation. This paper proposes a novel transition system, arc-swift, that enables direct attachments between tokens farther apart with a single transition. This allows the parser to leverage lexical information more directly in transition decisions. Hence, arc-swift can achieve significantly better performance with a very small beam size. Our parsers reduce error by 3.7--7.6 Treebank dependency parsing task and English Universal Dependencies.