Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs

29 Jan 2020  ยท  Leonardo F. R. Ribeiro, Yue Zhang, Claire Gardent, Iryna Gurevych ยท

Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations. Global node encoding allows explicit communication between two distant nodes, thereby neglecting graph topology as all nodes are directly connected. In contrast, local node encoding considers the relations between neighbor nodes capturing the graph structure, but it can fail to capture long-range relations. In this work, we gather both encoding strategies, proposing novel neural models which encode an input graph combining both global and local node contexts, in order to learn better contextualized node embeddings. In our experiments, we demonstrate that our approaches lead to significant improvements on two graph-to-text datasets achieving BLEU scores of 18.01 on AGENDA dataset, and 63.69 on the WebNLG dataset for seen categories, outperforming state-of-the-art models by 3.7 and 3.1 points, respectively.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
KG-to-Text Generation AGENDA CGE-LW BLEU 18.01 # 4
Graph-to-Sequence WebNLG CGE-LW BLEU 63.69 # 1
Data-to-Text Generation WebNLG CGE-LW (Levi Graph) BLEU 63.69 # 9


No methods listed for this paper. Add relevant methods here