Graph-to-Sequence Learning using Gated Graph Neural Networks
arXiv:1806.09835
Abstract
Many NLP applications can be framed as a graph-to-sequence learning problem. Previous work proposing neural architectures on this setting obtained promising results compared to grammar-based approaches but still rely on linearisation heuristics and/or standard recurrent networks to achieve the best performance. In this work, we propose a new model that encodes the full structural information contained in the graph. Our architecture couples the recently proposed Gated Graph Neural Networks with an input transformation that allows nodes and edges to have their own hidden representations, while tackling the parameter explosion problem present in previous work. Experimental results show that our model outperforms strong baselines in generation from AMR graphs and syntax-based neural machine translation.
arXiv commentACL 2018
References in corpus (8)
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- Molecular Graph Convolutions: Moving Beyond Fingerprints
- Convolutional Networks on Graphs for Learning Molecular Fingerprints
- Sockeye: A Toolkit for Neural Machine Translation
- Modeling Relational Data with Graph Convolutional Networks
- Tree-to-Sequence Attentional Neural Machine Translation
- Learning to Parse and Translate Improves Neural Machine Translation
- AMR-to-text Generation with Synchronous Node Replacement Grammar