Deep Graph Convolutional Encoders for Structured Data to Text Generation

10/23/2018

∙

by   Diego Marcheggiani, et al.

∙

0

∙

share

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.