@inproceedings{kale-rastogi-2020-text,
    title = "Text-to-Text Pre-Training for Data-to-Text Tasks",
    author = "Kale, Mihir  and
      Rastogi, Abhinav",
    editor = "Davis, Brian  and
      Graham, Yvette  and
      Kelleher, John  and
      Sripada, Yaji",
    booktitle = "Proceedings of the 13th International Conference on Natural Language Generation",
    month = dec,
    year = "2020",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.inlg-1.14/",
    doi = "10.18653/v1/2020.inlg-1.14",
    pages = "97--102",
    abstract = "We study the pre-train + fine-tune strategy for data-to-text tasks. Our experiments indicate that text-to-text pre-training in the form of T5 (Raffel et al., 2019), enables simple, end-to-end transformer based models to outperform pipelined neural architectures tailored for data-to-text generation, as well as alternatives such as BERT and GPT-2. Importantly, T5 pre-training leads to better generalization, as evidenced by large improvements on out-ofdomain test sets. We hope our work serves as a useful baseline for future research, as transfer learning becomes ever more prevalent for data-to-text tasks."
}