@inproceedings{xie-etal-2022-unifiedskg,
    title = "{U}nified{SKG}: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models",
    author = "Xie, Tianbao  and
      Wu, Chen Henry  and
      Shi, Peng  and
      Zhong, Ruiqi  and
      Scholak, Torsten  and
      Yasunaga, Michihiro  and
      Wu, Chien-Sheng  and
      Zhong, Ming  and
      Yin, Pengcheng  and
      Wang, Sida I.  and
      Zhong, Victor  and
      Wang, Bailin  and
      Li, Chengzu  and
      Boyle, Connor  and
      Ni, Ansong  and
      Yao, Ziyu  and
      Radev, Dragomir  and
      Xiong, Caiming  and
      Kong, Lingpeng  and
      Zhang, Rui  and
      Smith, Noah A.  and
      Zettlemoyer, Luke  and
      Yu, Tao",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.39",
    pages = "602--631",
    abstract = "Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases. Since the inputs and outputs of SKG tasks are heterogeneous, they have been studied separately by different communities, which limits systematic and compatible research on SKG. In this paper, we overcome this limitation by proposing the UnifiedSKG framework, which unifies 21 SKG tasks into a text-to-text format, aiming to promote systematic SKG research, instead of being exclusive to a single task, domain, or dataset. We use UnifiedSKG to benchmark T5 with different sizes and show that T5, with simple modifications when necessary, achieves state-of-the-art performance on almost all of the 21 tasks. We further demonstrate that multi-task prefix-tuning improves the performance on most tasks, largely improving the overall performance. UnifiedSKG also facilitates the investigation of zero-shot and few-shot learning, and we show that T0, GPT-3, and Codex struggle in zero-shot and few-shot learning for SKG. We also use UnifiedSKG to conduct a series of controlled experiments on structured knowledge encoding variants across SKG tasks. UnifiedSKG is easily extensible to more tasks, and it is open-sourced at https://github.com/hkunlp/unifiedskg.",
}