A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling. (arXiv:1701.02593v1 [cs.CL])

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 respectable 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 CoNLL-2009 dataset. 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 the standard out-of-domain test set.

from cs.AI updates on arXiv.org http://ift.tt/2iDgCeU
via IFTTT