Joint model for parsing syntactic and semantic dependencies

Xavier Lluís, Lluis Marques

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

9 Citations (Scopus)

Abstract

This paper describes a system that jointly parses syntactic and semantic dependencies, presented at the CoNLL-2008 shared task (Surdeanu et al., 2008). It combines online Peceptron learning (Collins, 2002) with a parsing model based on the Eisner algorithm (Eisner, 1996), extended so as to jointly assign syntactic and semantic labels. Overall results are 78.11 global F 1, 85.84 LAS, 70.35 semantic F 1. Official results for the shared task (63.29 global F 1; 71.95 LAS; 54.52 semantic F 1) were significantly lower due to bugs present at submission time.

Original languageEnglish
Title of host publicationCoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning
Pages188-192
Number of pages5
Publication statusPublished - 1 Dec 2008
Externally publishedYes
Event12th Conference on Computational Natural Language Learning, CoNLL 2008 - Manchester, United Kingdom
Duration: 16 Aug 200817 Aug 2008

Other

Other12th Conference on Computational Natural Language Learning, CoNLL 2008
CountryUnited Kingdom
CityManchester
Period16/8/0817/8/08

Fingerprint

Syntactics
Semantics
semantics
Labels
present
learning

ASJC Scopus subject areas

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

Cite this

Lluís, X., & Marques, L. (2008). Joint model for parsing syntactic and semantic dependencies. In CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning (pp. 188-192)

Joint model for parsing syntactic and semantic dependencies. / Lluís, Xavier; Marques, Lluis.

CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. p. 188-192.

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

Lluís, X & Marques, L 2008, Joint model for parsing syntactic and semantic dependencies. in CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. pp. 188-192, 12th Conference on Computational Natural Language Learning, CoNLL 2008, Manchester, United Kingdom, 16/8/08.
Lluís X, Marques L. Joint model for parsing syntactic and semantic dependencies. In CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. p. 188-192
Lluís, Xavier ; Marques, Lluis. / Joint model for parsing syntactic and semantic dependencies. CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. pp. 188-192
@inproceedings{6738d6b1a12d4ecbbfdee5eea1a6b313,
title = "Joint model for parsing syntactic and semantic dependencies",
abstract = "This paper describes a system that jointly parses syntactic and semantic dependencies, presented at the CoNLL-2008 shared task (Surdeanu et al., 2008). It combines online Peceptron learning (Collins, 2002) with a parsing model based on the Eisner algorithm (Eisner, 1996), extended so as to jointly assign syntactic and semantic labels. Overall results are 78.11 global F 1, 85.84 LAS, 70.35 semantic F 1. Official results for the shared task (63.29 global F 1; 71.95 LAS; 54.52 semantic F 1) were significantly lower due to bugs present at submission time.",
author = "Xavier Llu{\'i}s and Lluis Marques",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "1905593481",
pages = "188--192",
booktitle = "CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning",

}

TY - GEN

T1 - Joint model for parsing syntactic and semantic dependencies

AU - Lluís, Xavier

AU - Marques, Lluis

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper describes a system that jointly parses syntactic and semantic dependencies, presented at the CoNLL-2008 shared task (Surdeanu et al., 2008). It combines online Peceptron learning (Collins, 2002) with a parsing model based on the Eisner algorithm (Eisner, 1996), extended so as to jointly assign syntactic and semantic labels. Overall results are 78.11 global F 1, 85.84 LAS, 70.35 semantic F 1. Official results for the shared task (63.29 global F 1; 71.95 LAS; 54.52 semantic F 1) were significantly lower due to bugs present at submission time.

AB - This paper describes a system that jointly parses syntactic and semantic dependencies, presented at the CoNLL-2008 shared task (Surdeanu et al., 2008). It combines online Peceptron learning (Collins, 2002) with a parsing model based on the Eisner algorithm (Eisner, 1996), extended so as to jointly assign syntactic and semantic labels. Overall results are 78.11 global F 1, 85.84 LAS, 70.35 semantic F 1. Official results for the shared task (63.29 global F 1; 71.95 LAS; 54.52 semantic F 1) were significantly lower due to bugs present at submission time.

UR - http://www.scopus.com/inward/record.url?scp=77949625356&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949625356&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1905593481

SN - 9781905593484

SP - 188

EP - 192

BT - CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning

ER -