A second-order Joint Eisner model for syntactic and semantic dependency parsing

Xavier Lluís, Stefan Bott, Lluis Marques

Research output: Chapter in Book/Report/Conference proceedingChapter

7 Citations (Scopus)

Abstract

We present a system developed for the CoNLL-2009 Shared Task (Hajič et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1.

Original languageEnglish
Title of host publicationCoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task
Pages79-84
Number of pages6
Publication statusPublished - 1 Dec 2009
Externally publishedYes
Event13th Conference on Computational Natural Language Learning, CoNLL 2009 - Boulder, CO, United States
Duration: 4 Jun 20094 Jun 2009

Other

Other13th Conference on Computational Natural Language Learning, CoNLL 2009
CountryUnited States
CityBoulder, CO
Period4/6/094/6/09

Fingerprint

Syntactics
Semantics
semantics
learning method
Macros
Neural networks
language

ASJC Scopus subject areas

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

Cite this

Lluís, X., Bott, S., & Marques, L. (2009). A second-order Joint Eisner model for syntactic and semantic dependency parsing. In CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task (pp. 79-84)

A second-order Joint Eisner model for syntactic and semantic dependency parsing. / Lluís, Xavier; Bott, Stefan; Marques, Lluis.

CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task. 2009. p. 79-84.

Research output: Chapter in Book/Report/Conference proceedingChapter

Lluís, X, Bott, S & Marques, L 2009, A second-order Joint Eisner model for syntactic and semantic dependency parsing. in CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task. pp. 79-84, 13th Conference on Computational Natural Language Learning, CoNLL 2009, Boulder, CO, United States, 4/6/09.
Lluís X, Bott S, Marques L. A second-order Joint Eisner model for syntactic and semantic dependency parsing. In CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task. 2009. p. 79-84
Lluís, Xavier ; Bott, Stefan ; Marques, Lluis. / A second-order Joint Eisner model for syntactic and semantic dependency parsing. CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task. 2009. pp. 79-84
@inbook{5d4011427826444b8d79da56e29b4670,
title = "A second-order Joint Eisner model for syntactic and semantic dependency parsing",
abstract = "We present a system developed for the CoNLL-2009 Shared Task (Hajič et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1.",
author = "Xavier Llu{\'i}s and Stefan Bott and Lluis Marques",
year = "2009",
month = "12",
day = "1",
language = "English",
pages = "79--84",
booktitle = "CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task",

}

TY - CHAP

T1 - A second-order Joint Eisner model for syntactic and semantic dependency parsing

AU - Lluís, Xavier

AU - Bott, Stefan

AU - Marques, Lluis

PY - 2009/12/1

Y1 - 2009/12/1

N2 - We present a system developed for the CoNLL-2009 Shared Task (Hajič et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1.

AB - We present a system developed for the CoNLL-2009 Shared Task (Hajič et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1.

UR - http://www.scopus.com/inward/record.url?scp=80053417203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053417203&partnerID=8YFLogxK

M3 - Chapter

SP - 79

EP - 84

BT - CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task

ER -