Projective dependency parsing with perceptron

Xavier Carreras, Mihai Surdeanu, Lluis Marques

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

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 surfacetext distance between tokens, and the syntactic context dominated by each dependency. In experiments, the treatment of multilingual information was totally blind.

Original languageEnglish
Title of host publicationProceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X
Publication statusPublished - 1 Dec 2006
Externally publishedYes
Event10th Conference on Computational Natural Language Learning, CoNLL-X - New York, NY, United States
Duration: 8 Jun 20069 Jun 2006

Other

Other10th Conference on Computational Natural Language Learning, CoNLL-X
CountryUnited States
CityNew York, NY
Period8/6/069/6/06

Fingerprint

Neural networks
experiment
Syntactics
Experiments
learning

ASJC Scopus subject areas

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

Cite this

Carreras, X., Surdeanu, M., & Marques, L. (2006). Projective dependency parsing with perceptron. In Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X

Projective dependency parsing with perceptron. / Carreras, Xavier; Surdeanu, Mihai; Marques, Lluis.

Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X. 2006.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Carreras, X, Surdeanu, M & Marques, L 2006, Projective dependency parsing with perceptron. in Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X. 10th Conference on Computational Natural Language Learning, CoNLL-X, New York, NY, United States, 8/6/06.
Carreras X, Surdeanu M, Marques L. Projective dependency parsing with perceptron. In Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X. 2006
Carreras, Xavier ; Surdeanu, Mihai ; Marques, Lluis. / Projective dependency parsing with perceptron. Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X. 2006.
@inproceedings{833aeb7aba9b4cc48cf198c61f7f1128,
title = "Projective dependency parsing with perceptron",
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 surfacetext distance between tokens, and the syntactic context dominated by each dependency. In experiments, the treatment of multilingual information was totally blind.",
author = "Xavier Carreras and Mihai Surdeanu and Lluis Marques",
year = "2006",
month = "12",
day = "1",
language = "English",
booktitle = "Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X",

}

TY - GEN

T1 - Projective dependency parsing with perceptron

AU - Carreras, Xavier

AU - Surdeanu, Mihai

AU - Marques, Lluis

PY - 2006/12/1

Y1 - 2006/12/1

N2 - 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 surfacetext distance between tokens, and the syntactic context dominated by each dependency. In experiments, the treatment of multilingual information was totally blind.

AB - 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 surfacetext distance between tokens, and the syntactic context dominated by each dependency. In experiments, the treatment of multilingual information was totally blind.

UR - http://www.scopus.com/inward/record.url?scp=84862288778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862288778&partnerID=8YFLogxK

M3 - Conference contribution

BT - Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X

ER -