%0 Conference Proceedings %T A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling %A Marcheggiani, Diego %A Frolov, Anton %A Titov, Ivan %Y Levy, Roger %Y Specia, Lucia %S Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017) %D 2017 %8 August %I Association for Computational Linguistics %C Vancouver, Canada %F marcheggiani-etal-2017-simple %X We introduce a simple and accurate neural model for dependency-based semantic role labeling. Our model predicts predicate-argument dependencies relying on states of a bidirectional LSTM encoder. The semantic role labeler achieves competitive performance on English, even without any kind of syntactic information and only using local inference. However, when automatically predicted part-of-speech tags are provided as input, it substantially outperforms all previous local models and approaches the best reported results on the English CoNLL-2009 dataset. We also consider Chinese, Czech and Spanish where our approach also achieves competitive results. Syntactic parsers are unreliable on out-of-domain data, so standard (i.e., syntactically-informed) SRL models are hindered when tested in this setting. Our syntax-agnostic model appears more robust, resulting in the best reported results on standard out-of-domain test sets. %R 10.18653/v1/K17-1041 %U https://aclanthology.org/K17-1041 %U https://doi.org/10.18653/v1/K17-1041 %P 411-420