Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

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.

To appear in EMNLP 2017

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• Neural Message Passing for Quantum Chemistry
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Discriminative Neural Sentence Modeling by Tree-Based Convolution
• Learning to Parse and Translate Improves Neural Machine Translation

Cited by in corpus (23)

• Residual Gated Graph ConvNets
• Benchmarking Graph Neural Networks
• An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem
• Natural Language Processing Advancements By Deep Learning: A Survey
• Glyce: Glyph-vectors for Chinese Character Representations
• Learning to Generate Questions by Learning What not to Generate
• Learning the Travelling Salesperson Problem Requires Rethinking Generalization
• Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
• PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
• StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling
• Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks
• Lattice CNNs for Matching Based Chinese Question Answering
• Graph Neural Lasso for Dynamic Network Regression
• Fake Sentence Detection as a Training Task for Sentence Encoding
• Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models
• Learning Graph Pooling and Hybrid Convolutional Operations for Text Representations
• Interactive Reinforcement Learning for Feature Selection with Decision Tree in the Loop
• Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification
• ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks
• Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks
• Edge-Labeling based Directed Gated Graph Network for Few-shot Learning
• "Killing Me" Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism
• Edge-featured Graph Neural Architecture Search