Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning
Open Access
- 1 November 2019
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 7, 297-312
- https://doi.org/10.1162/tacl_a_00269
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 Network (DCGCN). 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 AMR-to-text generation and syntax-based neural machine translation. 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 Network (DCGCN). 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 AMR-to-text generation and syntax-based neural machine translation. 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 Network (DCGCN). 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 AMR-to-text generation and syntax-based neural machine translation.Keywords
This publication has 7 references indexed in Scilit:
- Densely Connected Convolutional NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- High Prevalence of Assisted Injection Among Street-Involved Youth in a Canadian SettingAIDS and Behavior, 2015
- Handbook of Graph TheoryPublished by Taylor & Francis Ltd ,2013
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- A new model for learning in graph domainsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Long Short-Term MemoryNeural Computation, 1997
- Finding Structure in TimeCognitive Science, 1990