A non-monotonic Arc-Eager transition system for dependency parsing

Matthew Honnibal, Yoav Goldberg, Mark Johnson

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Previous incremental parsers have used monotonic state transitions. However, transitions can be made to revise previous decisions quite naturally, based on further information. We show that a simple adjustment to the Arc-Eager transition system to relax its monotonicity constraints can improve accuracy, so long as the training data includes examples of mistakes for the non-monotonic transitions to repair. We evaluate the change in the context of a state-of-the-art system, and obtain a statistically significant improvement (p < 0.001) on the English evaluation and 5/10 of the CoNLL languages.

Original languageEnglish
Title of host publicationCoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages163-172
Number of pages10
ISBN (Electronic)9781937284701
StatePublished - 2013
Event17th Conference on Computational Natural Language Learning, CoNLL 2013 - Sofia, Bulgaria
Duration: 8 Aug 20139 Aug 2013

Publication series

NameCoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings

Conference

Conference17th Conference on Computational Natural Language Learning, CoNLL 2013
Country/TerritoryBulgaria
CitySofia
Period8/08/139/08/13

All Science Journal Classification (ASJC) codes

  • Linguistics and Language
  • Artificial Intelligence
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'A non-monotonic Arc-Eager transition system for dependency parsing'. Together they form a unique fingerprint.

Cite this