his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • 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
Labeled Pseudo-Projective Dependency Parsing with Support Vector Machines
Show others and affiliations
2006 (English)In: the Tenth Conference on Computational Natural Language Learning (CoNLL), 2006, 221-225 p.Conference paper, (Other academic)
Abstract [en]

We use SVMclassifiers to predict the next action of a deterministic parser that builds labeled projective dependency graphs in an incremental fashion. Non-projective dependencies are captured indirectly by projectivizing the training data for the classifiers and applying an inverse transformation to the output of the parser. We present evaluation results and an error analysis focusing on Swedish and Turkish.

Place, publisher, year, edition, pages
2006. 221-225 p.
Identifiers
URN: urn:nbn:se:his:diva-1927Scopus ID: 2-s2.0-84862271629OAI: oai:DiVA.org:his-1927DiVA: diva2:32203
Conference
10th Conference on Computational Natural Language Learning, CoNLL-X;New York, NY;8 June 2006through9 June 2006
Available from: 2007-09-21 Created: 2007-09-21 Last updated: 2013-03-20

Open Access in DiVA

No full text

Scopus

Search in DiVA

By author/editor
Marinov, Svetoslav
By organisation
School of Humanities and Informatics

Search outside of DiVA

GoogleGoogle Scholar

Total: 15 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • 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