An improved non-monotonic transition system for dependency parsing

Matthew Honnibal, Mark Johnson

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

133 Citations (Scopus)

Abstract

Transition-based dependency parsers usually use transition systems that monotonically extend partial parse states until they identify a complete parse tree. Honnibal et al. (2013) showed that greedy onebest parsing accuracy can be improved by adding additional non-monotonic transitions that permit the parser to "repair" earlier parsing mistakes by "over-writing" earlier parsing decisions. This increases the size of the set of complete parse trees that each partial parse state can derive, enabling such a parser to escape the "garden paths" that can trap monotonic greedy transition-based dependency parsers. We describe a new set of non-monotonic transitions that permits a partial parse state to derive a larger set of completed parse trees than previous work, which allows our parser to escape from a larger set of garden paths. A parser with our new nonmonotonic transition system has 91.85% directed attachment accuracy, an improvement of 0.6% over a comparable parser using the standard monotonic arc-eager transitions.

Original languageEnglish
Title of host publicationConference on Empirical Methods in Natural Language Processing, EMNLP 2015
Subtitle of host publicationConference Proceedings
Place of PublicationRed Hook, NY
PublisherAssociation for Computational Linguistics (ACL)
Pages1373-1378
Number of pages6
ISBN (Electronic)9781941643327
Publication statusPublished - 2015
EventConference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal
Duration: 17 Sep 201521 Sep 2015

Other

OtherConference on Empirical Methods in Natural Language Processing, EMNLP 2015
CountryPortugal
CityLisbon
Period17/09/1521/09/15

Fingerprint Dive into the research topics of 'An improved non-monotonic transition system for dependency parsing'. Together they form a unique fingerprint.

Cite this