Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning

2019/08/16 by Zhijiang Guo, Yan Zhang, Guo, Zhijiang +5 · 1 citation
Computer Science · #Advanced Graph Neural Networks #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1908.05957

openalex publication_date 2019/08/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We focus on graph-to-sequence learning, which can be framed as transducing graph structures to sequences for text generation. To capture structural information associated with graphs, we investigate the problem of encoding graphs using graph convolutional networks (GCNs). Unlike various existing approaches where shallow architectures were used for capturing local structural information only, we introduce a dense connection strategy, proposing a novel Densely Connected Graph Convolutional Networks (DCGCNs). Such a deep architecture is able to integrate both local and non-local features to learn a better structural representation of a graph. Our model outperforms the state-of-the-art neural models significantly on AMRto-text generation and syntax-based neural machine translation.

Citations

• Sequence to Sequence Learning with Neural Networks
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems

Cited by

• Forecasting West Nile virus with deep graph encoders

Related

• Deep Graph Convolutional Encoders for Structured Data to Text Generation
• Graph-to-Sequence Learning using Gated Graph Neural Networks
• Graph Learning Network: A Structure Learning Algorithm
• Learning Graph Pooling and Hybrid Convolutional Operations for Text Representations
• Structured Sequence Modeling with Graph Convolutional Recurrent Networks