A Combined Memory-Based Semantic Role Labeler of English
Roser Morante, Walter Daelemans and Vincent Van Asch
In: 12th Conference on Computational Natural Language Learning, 16-17 Aug 2008, Manchester, UK.
In this paper we describe the system submitted
to the closed challenge of the
CoNLL-2008 shared task on joint parsing
of syntactic and semantic dependencies.
The system that we present extracts syntactic
and semantic dependencies independently.
Syntactic dependencies are processed
with the MaltParser 0.4. Semantic
dependencies are processed with a combination
of memory-based classifiers. We
focus on the memory-based semantic role
labeler, which achieves 71,88 labeled F1.