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

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.