Model Description

We release our best performing models for the WebNLG and EventNarrative datasets from the paper GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation. Our model is intended to be used on knowledge graphs in order to narrate their contents, giving a verbalization of the structured data.

Paper

Please see our paper here.

Citation

If you found this model useful, please consider citing our paper:

@inproceedings{colas-etal-2022-gap,
    title = "{GAP}: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation",
    author = "Colas, Anthony  and
      Alvandipour, Mehrdad  and
      Wang, Daisy Zhe",
    booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2022.coling-1.506",
    pages = "5755--5769"
}

GitHub repo

Please see our GitHub here.