UBC-UPC

Sequential SRL using selectional preferences. An aproach with maximum entropy Markov models

Beñat Zapirain, Eneko Agirre, Lluis Marques

Research output: Contribution to conferencePaper

7 Citations (Scopus)

Abstract

We present a sequential Semantic Role Labeling system that describes the tagging problem as a Maximum Entropy Markov Model. The system uses full syntactic information to select BIO-tokens from input data, and classifies them sequentially using state-of-the-art features, with the addition of Selectional Preference features. The system presented achieves competitive performance in the CoNLL-2005 shared task dataset and it ranks first in the SRL subtask of the Semeval-2007 task 17.

Original languageEnglish
Pages354-357
Number of pages4
Publication statusPublished - 1 Jan 2007
Event4th International Workshop on Semantic Evaluations, SemEval 2007 - Prague, Czech Republic
Duration: 23 Jun 200724 Jun 2007

Other

Other4th International Workshop on Semantic Evaluations, SemEval 2007
CountryCzech Republic
CityPrague
Period23/6/0724/6/07

Fingerprint

Maximum Entropy
Syntactics
Labeling
Markov Model
Entropy
Semantics
Tagging
Classify

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Theoretical Computer Science

Cite this

Zapirain, B., Agirre, E., & Marques, L. (2007). UBC-UPC: Sequential SRL using selectional preferences. An aproach with maximum entropy Markov models. 354-357. Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic.

UBC-UPC : Sequential SRL using selectional preferences. An aproach with maximum entropy Markov models. / Zapirain, Beñat; Agirre, Eneko; Marques, Lluis.

2007. 354-357 Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic.

Research output: Contribution to conferencePaper

Zapirain, B, Agirre, E & Marques, L 2007, 'UBC-UPC: Sequential SRL using selectional preferences. An aproach with maximum entropy Markov models' Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic, 23/6/07 - 24/6/07, pp. 354-357.
Zapirain B, Agirre E, Marques L. UBC-UPC: Sequential SRL using selectional preferences. An aproach with maximum entropy Markov models. 2007. Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic.
Zapirain, Beñat ; Agirre, Eneko ; Marques, Lluis. / UBC-UPC : Sequential SRL using selectional preferences. An aproach with maximum entropy Markov models. Paper presented at 4th International Workshop on Semantic Evaluations, SemEval 2007, Prague, Czech Republic.4 p.
@conference{8ff63e074aef48289dc878142c939061,
title = "UBC-UPC: Sequential SRL using selectional preferences. An aproach with maximum entropy Markov models",
abstract = "We present a sequential Semantic Role Labeling system that describes the tagging problem as a Maximum Entropy Markov Model. The system uses full syntactic information to select BIO-tokens from input data, and classifies them sequentially using state-of-the-art features, with the addition of Selectional Preference features. The system presented achieves competitive performance in the CoNLL-2005 shared task dataset and it ranks first in the SRL subtask of the Semeval-2007 task 17.",
author = "Be{\~n}at Zapirain and Eneko Agirre and Lluis Marques",
year = "2007",
month = "1",
day = "1",
language = "English",
pages = "354--357",
note = "4th International Workshop on Semantic Evaluations, SemEval 2007 ; Conference date: 23-06-2007 Through 24-06-2007",

}

TY - CONF

T1 - UBC-UPC

T2 - Sequential SRL using selectional preferences. An aproach with maximum entropy Markov models

AU - Zapirain, Beñat

AU - Agirre, Eneko

AU - Marques, Lluis

PY - 2007/1/1

Y1 - 2007/1/1

N2 - We present a sequential Semantic Role Labeling system that describes the tagging problem as a Maximum Entropy Markov Model. The system uses full syntactic information to select BIO-tokens from input data, and classifies them sequentially using state-of-the-art features, with the addition of Selectional Preference features. The system presented achieves competitive performance in the CoNLL-2005 shared task dataset and it ranks first in the SRL subtask of the Semeval-2007 task 17.

AB - We present a sequential Semantic Role Labeling system that describes the tagging problem as a Maximum Entropy Markov Model. The system uses full syntactic information to select BIO-tokens from input data, and classifies them sequentially using state-of-the-art features, with the addition of Selectional Preference features. The system presented achieves competitive performance in the CoNLL-2005 shared task dataset and it ranks first in the SRL subtask of the Semeval-2007 task 17.

UR - http://www.scopus.com/inward/record.url?scp=45749109014&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=45749109014&partnerID=8YFLogxK

M3 - Paper

SP - 354

EP - 357

ER -