@inproceedings{castro-ferreira-etal-2021-enriching,
    title = "Enriching the {E}2{E} dataset",
    author = "Castro Ferreira, Thiago  and
      Vaz, Helena  and
      Davis, Brian  and
      Pagano, Adriana",
    editor = "Belz, Anya  and
      Fan, Angela  and
      Reiter, Ehud  and
      Sripada, Yaji",
    booktitle = "Proceedings of the 14th International Conference on Natural Language Generation",
    month = aug,
    year = "2021",
    address = "Aberdeen, Scotland, UK",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2021.inlg-1.18/",
    doi = "10.18653/v1/2021.inlg-1.18",
    pages = "177--183",
    abstract = "This study introduces an enriched version of the E2E dataset, one of the most popular language resources for data-to-text NLG. We extract intermediate representations for popular pipeline tasks such as discourse ordering, text structuring, lexicalization and referring expression generation, enabling researchers to rapidly develop and evaluate their data-to-text pipeline systems. The intermediate representations are extracted by aligning non-linguistic and text representations through a process called delexicalization, which consists in replacing input referring expressions to entities/attributes with placeholders. The enriched dataset is publicly available."
}