Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

TL;DR

This paper introduces a novel approach combining graph convolutional networks with LSTMs to improve semantic role labeling by leveraging syntactic dependency structures, achieving state-of-the-art results on benchmark datasets.

Contribution

The paper presents a new GCN-based sentence encoder that, when combined with LSTMs, enhances SRL performance by effectively modeling syntactic dependencies.

Findings

GCNs are effective for encoding syntactic structures in SRL.

Combining GCNs with LSTMs outperforms previous models.

Achieved best scores on CoNLL-2009 for Chinese and English.

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.