Semantic Role Labeling Tools Trained on the Cast3LB-CoNNL-SemRol Corpus

AbstractIn this paper we present the Cast3LB-CoNLL-SemRol corpus, currently the only corpus of Spanish annotated with dependency syntax and semantic roles, and the tools that have been trained on the corpus: an ensemble of parsers and two dependency-based semantic role labelers that are the only semantic role labelers based on dependency syntax available for Spanish at this moment. One of the systems uses information from gold standard syntax, whereas the other one uses information from predicted syntax. The results of the first system (86 F1) are comparable to current state of the art results for constituent-based semantic role labeling of Spanish. The results of the second are 11 points lower. This work has been carried out as part of the project Técnicas semiautomáticas para el etiquetado de roles semánticos en corpus del español.