uu.seUppsala University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Arc-Hybrid Non-Projective Dependency Parsing with a Static-Dynamic Oracle
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Languages, Department of Linguistics and Philology. (Computational Linguistics)ORCID iD: 0000-0001-8844-2126
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Languages, Department of Linguistics and Philology. (Computational Linguistics)
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Languages, Department of Linguistics and Philology. (Computational Linguistics)
2017 (English)In: IWPT 2017 15th International Conference on Parsing Technologies: Proceedings of the Conference, Pisa, Italy: Association for Computational Linguistics, 2017, 99-104 p.Conference paper, Published paper (Refereed)
Abstract [en]

We extend the arc-hybrid transition system for dependency parsing with a SWAP transition that enables reordering of the words and construction of non-projective trees. Although this extension potentially breaks the arc-decomposability of the transition system, we show that the existing dynamic oracle can be modified and combined with a static oracle for the SWAP transition. Experiments on five languages with different degrees of non-projectivity show that the new system gives competitive accuracy and is significantly better than a system trained with a purely static oracle.

Place, publisher, year, edition, pages
Pisa, Italy: Association for Computational Linguistics, 2017. 99-104 p.
Keyword [en]
dependency parsing dynamic oracles online reordering
National Category
Language Technology (Computational Linguistics)
Research subject
Computational Linguistics
Identifiers
URN: urn:nbn:se:uu:diva-333442ISBN: 978-1-945626-73-9 (electronic)OAI: oai:DiVA.org:uu-333442DiVA: diva2:1156634
Conference
15th International Conference on Parsing Technologies, (IWPT 2017), September 20-22, 2017, Pisa, Italy
Available from: 2017-11-13 Created: 2017-11-13 Last updated: 2017-11-15Bibliographically approved

Open Access in DiVA

fulltext(132 kB)3 downloads
File information
File name FULLTEXT01.pdfFile size 132 kBChecksum SHA-512
1a09ef88b3487f5949a696963e36213588c218bb0102fb8645d034bf7c239532036a6206ae1e834a424fba1e5a50d974f435d708353ca2cd4be657a7365fab4c
Type fulltextMimetype application/pdf

Other links

http://compling.ucdavis.edu/iwpt2017/proceedings/pdf/IWPT14.pdf

Authority records BETA

de Lhoneux, MiryamStymne, SaraNivre, Joakim

Search in DiVA

By author/editor
de Lhoneux, MiryamStymne, SaraNivre, Joakim
By organisation
Department of Linguistics and Philology
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
Total: 3 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 15 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf