@inproceedings{schmitt-etal-2021-modeling,
    title = "Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs",
    author = {Schmitt, Martin  and
      Ribeiro, Leonardo F. R.  and
      Dufter, Philipp  and
      Gurevych, Iryna  and
      Sch{\"u}tze, Hinrich},
    editor = "Panchenko, Alexander  and
      Malliaros, Fragkiskos D.  and
      Logacheva, Varvara  and
      Jana, Abhik  and
      Ustalov, Dmitry  and
      Jansen, Peter",
    booktitle = "Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.textgraphs-1.2",
    doi = "10.18653/v1/2021.textgraphs-1.2",
    pages = "10--21",
    abstract = "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.",
}