Work

Arc-swift: A Novel Transition System for Dependency Parsing

Year: 2017

Type: conference-paper

Abstract: 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%relative to those using existing transition systems on the Penn Treebank dependency parsing task and English Universal Dependencies.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/p17-2018

Authors: Peng Qi, Christopher D. Manning

Institution: Stanford University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Defense Advanced Research Projects Agency, Advanced Research Projects Agency, Air Force Research Laboratory

Award: G4713059963