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

arXiv: https://arxiv.org/abs/2006.09242 · HTML: https://mlsanity.com/paper/2006.09242/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2020.

## Built on by (most cited first, 3 of 3)

- [JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2106.10502/) (2021)
- [Structural Adapters in Pretrained Language Models for AMR-to-text Generation](https://mlsanity.com/paper/2103.09120/) (2021)
- [How to Train Your Agent to Read and Write](https://mlsanity.com/paper/2101.00916/) (2021)

## Abstract (arXiv)

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.