%0 Conference Proceedings
%T Deep Graph Convolutional Encoders for Structured Data to Text Generation
%A Marcheggiani, Diego
%A Perez-Beltrachini, Laura
%Y Krahmer, Emiel
%Y Gatt, Albert
%Y Goudbeek, Martijn
%S Proceedings of the 11th International Conference on Natural Language Generation
%D 2018
%8 November
%I Association for Computational Linguistics
%C Tilburg University, The Netherlands
%F marcheggiani-perez-beltrachini-2018-deep
%X 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.
%R 10.18653/v1/W18-6501
%U https://aclanthology.org/W18-6501
%U https://doi.org/10.18653/v1/W18-6501
%P 1-9