Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs
Martin
Schmitt
author
Leonardo
F
R
Ribeiro
author
Philipp
Dufter
author
Iryna
Gurevych
author
Hinrich
Schütze
author
2021-06
text
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
Association for Computational Linguistics
Mexico City, Mexico
conference publication
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.
schmitt-etal-2021-modeling
10.18653/v1/2021.textgraphs-1.2
https://aclanthology.org/2021.textgraphs-1.2
2021-06
10
21