Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs

We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors - facilitating the detection of global patterns. We represent the relation between two nodes as the length of the shortest path between them. Graformer learns to weight these node-node relations differently for different attention heads, thus virtually learning differently connected views of the input graph. We evaluate Graformer on two popular graph-to-text generation benchmarks, AGENDA and WebNLG, where it achieves strong performance while using many fewer parameters than other approaches.

PDF Abstract NAACL (TextGraphs) 2021 PDF NAACL (TextGraphs) 2021 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
KG-to-Text Generation AGENDA Graformer BLEU 17.80 # 5
Data-to-Text Generation WebNLG Graformer BLEU 61.15 # 11