Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

Diego Marcheggiani, Ivan Titov
3/14/2017
cs.CLcs.LG

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

Abstract

Semantic role labeling (SRL) is the task of identifying the predicate-argument structure of a sentence. It is typically regarded as an important step in the standard NLP pipeline. As the semantic representations are closely related to syntactic ones, we exploit syntactic information in our model. We propose a version of graph convolutional networks (GCNs), a recent class of neural networks operating on graphs, suited to model syntactic dependency graphs. GCNs over syntactic dependency trees are used as sentence encoders, producing latent feature representations of words in a sentence. We observe that GCN layers are complementary to LSTM ones: when we stack both GCN and LSTM layers, we obtain a substantial improvement over an already state-of-the-art LSTM SRL model, resulting in the best reported scores on the standard benchmark (CoNLL-2009) both for Chinese and English.

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

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

86% match1 repo1912017

GATology for Linguistics: What Syntactic Dependencies It Knows

84% match2023

Simple BERT Models for Relation Extraction and Semantic Role Labeling

83% match1 repo292019

Incorporating Deep Syntactic and Semantic Knowledge for Chinese Sequence Labeling with GCN

82% match2023

GraphIE: A Graph-Based Framework for Information Extraction

80% match1 repo1102018

AMR Parsing as Graph Prediction with Latent Alignment

80% match1 repo542018

Cite this paper

@article{marcheggiani2017encoding,
  title  = {Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling},
  author = {Diego Marcheggiani and Ivan Titov},
  year   = {2017},
  eprint = {1703.04826},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1703.04826}
}

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/1703.04826.svg)](https://codeofpaper.com/paper/1703.04826)

Discussion