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

## TL;DR

This paper introduces Densely Connected Graph Convolutional Networks (DCGCNs) for graph-to-sequence learning, effectively capturing both local and non-local graph features to improve text generation tasks.

## Contribution

The paper proposes a novel dense connection strategy in GCNs, enabling deeper architectures that better encode graph structures for sequence generation.

## Key findings

- Outperforms state-of-the-art models on AMR-to-text generation
- Achieves significant improvements in syntax-based neural machine translation
- Demonstrates the effectiveness of deep, densely connected GCNs in graph encoding

## 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.