Abstract : Semantic role labeling has seen tremendous progress in the last years, both for supervised and unsupervised approaches. The knowledge-based approaches have been neglected while they have shown to bring the best results to the related word sense disambiguation task. We contribute a simple knowledge-based system with an easy to reproduce specification. We also present a novel approach to handle the passive voice in the context of semantic role labeling that reduces the error rate in F1 by 15.7%, showing that significant improvements can be brought while retaining the key advantages of the approach: a simple approach which facilitates analysis of individual errors, does not need any hand-annotated corpora and which is not domain-specific.
https://hal-cea.archives-ouvertes.fr/cea-00932330
Contributor : Quentin Pradet
<>
Submitted on : Thursday, January 16, 2014 - 4:56:36 PM
Last modification on : Thursday, February 7, 2019 - 3:04:19 PM
Long-term archiving on: Thursday, April 17, 2014 - 9:49:58 AM
