articleJan 1, 2005GOLD OA

Online large-margin training of dependency parsers

RMRyan McDonaldKCKoby CrammerFPFernando Pereira

University of Pennsylvania

Indexed incrossref

Abstract

We present an effective training algorithm for linearly-scored dependency parsers that implements online large-margin multi-class training (Crammer and Singer, 2003; Crammer et al., 2003) on top of efficient parsing techniques for dependency trees (Eisner, 1996). The trained parsers achieve a competitive dependency accuracy for both English and Czech with no language specific enhancements.

Citation impact

816
total citations
FWCI
58.81
Percentile
100%
References
33
Citations per year

Authors

3

Topics & keywords

Topics
Keywords
  • Dependency (UML)
  • Dependency grammar
  • Computer science
  • Margin (machine learning)
  • Parsing
  • Artificial intelligence
  • Training (meteorology)
  • Natural language processing
No related works found for this paper.

Funding