A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

Diego Marcheggiani, Anton Frolov, Ivan Titov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
PublisherAssociation for Computational Linguistics (ACL)
Pages411–420
Number of pages6
ISBN (Electronic)978-1-945626-54-8
DOIs
Publication statusPublished - 4 Aug 2017
Event 21st Conference on Computational Natural Language Learning - Vancouver, Canada
Duration: 3 Aug 20174 Aug 2017
http://www.conll.org/2017

Conference

Conference 21st Conference on Computational Natural Language Learning
Abbreviated titleCoNLL 2017
CountryCanada
CityVancouver
Period3/08/174/08/17
Internet address

Fingerprint Dive into the research topics of 'A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling'. Together they form a unique fingerprint.

Cite this