Semantic role labeling as sequential tagging

Lluis Marques, Pere Comas, Jesús Giménez, Neus Català

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

28 Citations (Scopus)

Abstract

In this paper we present a semantic role labeling system submitted to the CoNLL- 2005 shared task. The system makes use of partial and full syntactic information and converts the task into a sequential BIO-tagging. As a result, the labeling architecture is very simple. Building on a state-of-the-art set of features, a binary classifier for each label is trained using AdaBoost with fixed depth decision trees. The final system, which combines the outputs of two base systems performed F 1=76.59 on the official test set. Additionally, we provide results comparing the system when using partial vs. full parsing nput information.

Original languageEnglish
Title of host publicationCoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning
Pages193-196
Number of pages4
Publication statusPublished - 1 Dec 2005
Externally publishedYes
Event9th Conference on Computational Natural Language Learning, CoNLL 2005 - Ann Arbor, MI, United States
Duration: 29 Jun 200530 Jun 2005

Other

Other9th Conference on Computational Natural Language Learning, CoNLL 2005
CountryUnited States
CityAnn Arbor, MI
Period29/6/0530/6/05

Fingerprint

Labeling
Semantics
semantics
Adaptive boosting
Syntactics
Decision trees
Labels
Classifiers

ASJC Scopus subject areas

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

Cite this

Marques, L., Comas, P., Giménez, J., & Català, N. (2005). Semantic role labeling as sequential tagging. In CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning (pp. 193-196)

Semantic role labeling as sequential tagging. / Marques, Lluis; Comas, Pere; Giménez, Jesús; Català, Neus.

CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning. 2005. p. 193-196.

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

Marques, L, Comas, P, Giménez, J & Català, N 2005, Semantic role labeling as sequential tagging. in CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning. pp. 193-196, 9th Conference on Computational Natural Language Learning, CoNLL 2005, Ann Arbor, MI, United States, 29/6/05.
Marques L, Comas P, Giménez J, Català N. Semantic role labeling as sequential tagging. In CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning. 2005. p. 193-196
Marques, Lluis ; Comas, Pere ; Giménez, Jesús ; Català, Neus. / Semantic role labeling as sequential tagging. CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning. 2005. pp. 193-196
@inproceedings{7c6497ead9a1436ea8b61917bc962a59,
title = "Semantic role labeling as sequential tagging",
abstract = "In this paper we present a semantic role labeling system submitted to the CoNLL- 2005 shared task. The system makes use of partial and full syntactic information and converts the task into a sequential BIO-tagging. As a result, the labeling architecture is very simple. Building on a state-of-the-art set of features, a binary classifier for each label is trained using AdaBoost with fixed depth decision trees. The final system, which combines the outputs of two base systems performed F 1=76.59 on the official test set. Additionally, we provide results comparing the system when using partial vs. full parsing nput information.",
author = "Lluis Marques and Pere Comas and Jes{\'u}s Gim{\'e}nez and Neus Catal{\`a}",
year = "2005",
month = "12",
day = "1",
language = "English",
pages = "193--196",
booktitle = "CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning",

}

TY - GEN

T1 - Semantic role labeling as sequential tagging

AU - Marques, Lluis

AU - Comas, Pere

AU - Giménez, Jesús

AU - Català, Neus

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In this paper we present a semantic role labeling system submitted to the CoNLL- 2005 shared task. The system makes use of partial and full syntactic information and converts the task into a sequential BIO-tagging. As a result, the labeling architecture is very simple. Building on a state-of-the-art set of features, a binary classifier for each label is trained using AdaBoost with fixed depth decision trees. The final system, which combines the outputs of two base systems performed F 1=76.59 on the official test set. Additionally, we provide results comparing the system when using partial vs. full parsing nput information.

AB - In this paper we present a semantic role labeling system submitted to the CoNLL- 2005 shared task. The system makes use of partial and full syntactic information and converts the task into a sequential BIO-tagging. As a result, the labeling architecture is very simple. Building on a state-of-the-art set of features, a binary classifier for each label is trained using AdaBoost with fixed depth decision trees. The final system, which combines the outputs of two base systems performed F 1=76.59 on the official test set. Additionally, we provide results comparing the system when using partial vs. full parsing nput information.

UR - http://www.scopus.com/inward/record.url?scp=84862277098&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862277098&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84862277098

SP - 193

EP - 196

BT - CoNLL 2005 - Proceedings of the Ninth Conference on Computational Natural Language Learning

ER -