Most previous work on neural text generation from graph-structured data relies on standard sequence-to-sequence methods. These approaches linearise the input graph to be fed to a recurrent neural network. In this paper, we propose an alternative encoder based on graph convolutional networks that directly exploits the input structure. We report results on two graph-to-sequence datasets that empirically show the benefits of explicitly encoding the input graph structure.
@article{arxiv.1810.09995,
title = {Deep Graph Convolutional Encoders for Structured Data to Text Generation},
author = {Diego Marcheggiani and Laura Perez-Beltrachini},
journal= {arXiv preprint arXiv:1810.09995},
year = {2018}
}