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.
@article{arxiv.2006.09242,
title = {Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs},
author = {Martin Schmitt and Leonardo F. R. Ribeiro and Philipp Dufter and Iryna Gurevych and Hinrich Schütze},
journal= {arXiv preprint arXiv:2006.09242},
year = {2021}
}