Projective dependency parsing with perceptron

Xavier Carreras, Mihai Surdeanu, Lluís Màrquez

Research output: Contribution to conferencePaperpeer-review

Abstract

We describe an online learning dependency parser for the CoNLL-X Shared Task, based on the bottom-up projective algorithm of Eisner (2000). We experiment with a large feature set that models: the tokens involved in dependencies and their immediate context, the surface-text distance between tokens, and the syntactic context dominated by each dependency. In experiments, the treatment of multilingual information was totally blind.

Original languageEnglish (US)
Pages181-185
Number of pages5
StatePublished - 2006
Event10th Conference on Computational Natural Language Learning, CoNLL 2006 - New York City, United States
Duration: Jun 8 2006Jun 9 2006

Conference

Conference10th Conference on Computational Natural Language Learning, CoNLL 2006
Country/TerritoryUnited States
CityNew York City
Period6/8/066/9/06

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Projective dependency parsing with perceptron'. Together they form a unique fingerprint.

Cite this