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

Diego Marcheggiani, Anton Frolov, Ivan Titov
1/10/2017
cs.CLcs.AI

Official code: diegma/neural-dep-srl (191 stars, Apache-2.0, last commit 2021-02-20).

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 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.

View on arXivView PDF

Code Implementations(1)

diegma/neural-dep-srlOfficial100%
Apache-2.0

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

19133Perl, ShellJan 10, 20175 years agoApache-2.0

Similar Papers

Simple BERT Models for Relation Extraction and Semantic Role Labeling

88% match1 repo292019

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

86% match1 repo1912017

A Span Selection Model for Semantic Role Labeling

85% match1 repo452018

Persian Semantic Role Labeling Using Transfer Learning and BERT-Based Models

81% match2023

LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models

79% match2025

Generalizing Natural Language Analysis through Span-relation Representations

78% match1 repo912019

Cite this paper

@article{marcheggiani2017simple,
  title  = {A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling},
  author = {Diego Marcheggiani and Anton Frolov and Ivan Titov},
  year   = {2017},
  eprint = {1701.02593},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1701.02593}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1701.02593.svg)](https://codeofpaper.com/paper/1701.02593)

Discussion