Automatic semantic role labelling using a memory-based learning system
Roser Morante
(Roser.Morante@ua.ac.be)
Researcher, CNTS research group, University of Antwerp
Abstract
In this paper we present a semantic role labelling system. The main component of the system is a memory-based classifier. The system has been trained with the Cast3LB-CoNLL-SemRol. The features encode information from dependency syntax. The results (F1 0.86) are comparable with state-of-the-art results (F1 around 0.86) from systems that use information from constituent syntax.
Keywords
Submission date:
November 2007
Accepted in:
December 2007
Published in:
May 2008
The texts published in this journal, unless otherwise indicated, are subject to a Creative Commons Attribution-Noncommercial-NoDerivativeWorks 2.5 Spain licence. They may be copied, distributed and broadcast provided that the author and the e-journal that publishes them (Digithum) are cited. Commercial use and derivative works are not permitted. The full licence can be consulted on http://creativecommons.org/licenses/by-nc-nd/2.5/es/deed.en.