@inproceedings{perez-beltrachini-gardent-2017-analysing,
    title = "Analysing Data-To-Text Generation Benchmarks",
    author = "Perez-Beltrachini, Laura  and
      Gardent, Claire",
    editor = "Alonso, Jose M.  and
      Bugar{\'i}n, Alberto  and
      Reiter, Ehud",
    booktitle = "Proceedings of the 10th International Conference on Natural Language Generation",
    month = sep,
    year = "2017",
    address = "Santiago de Compostela, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/W17-3537/",
    doi = "10.18653/v1/W17-3537",
    pages = "238--242",
    abstract = "A generation system can only be as good as the data it is trained on. In this short paper, we propose a methodology for analysing data-to-text corpora used for training Natural Language Generation (NLG) systems. We apply this methodology to three existing benchmarks. We conclude by eliciting a set of criteria for the creation of a data-to-text benchmark which could help better support the development, evaluation and comparison of linguistically sophisticated data-to-text generators."
}