Show simple item record

dc.contributor.authorCarreras Pérez, Xavier
dc.contributor.authorSurdeanu, Mihai
dc.contributor.authorMàrquez Villodre, Lluís
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics
dc.identifier.citationCarreras, X.; Surdeanu, M.; Màrquez, L. Projective dependency parsing with perceptron. A: Conference on Computational Natural Language Learning. "Tenth Conference on Computational Natural Language Learning (CoNLL-X)". New York City: 2010, p. 181-185.
dc.description.abstractWe 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 surfacetext distance between tokens, and the syntactic context dominated by each dependency. In experiments, the treatment of multilingual information was totally blind.
dc.format.extent5 p.
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural
dc.subject.lcshComputational linguistics
dc.titleProjective dependency parsing with perceptron
dc.typeConference report
dc.subject.lemacLingüística computacional
dc.contributor.groupUniversitat Politècnica de Catalunya. GPLN - Grup de Processament del Llenguatge Natural
dc.description.peerreviewedPeer Reviewed
dc.rights.accessOpen Access
dc.description.versionPostprint (author’s final draft)
upcommons.citation.authorCarreras, X.; Surdeanu, M.; Màrquez, L.
upcommons.citation.contributorConference on Computational Natural Language Learning
upcommons.citation.pubplaceNew York City
upcommons.citation.publicationNameTenth Conference on Computational Natural Language Learning (CoNLL-X)

Files in this item


This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder