Deep Graph Convolutional Encoders for Structured Data to Text Generation

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.

PDF Abstract WS 2018 PDF WS 2018 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Data-to-Text Generation SR11Deep GCN + feat BLEU 0.666 # 2
Data-to-Text Generation WebNLG GCN EC BLEU 55.9 # 12

Methods