@inproceedings{wang-etal-2022-squality,
    title = "{SQ}u{ALITY}: Building a Long-Document Summarization Dataset the Hard Way",
    author = "Wang, Alex  and
      Pang, Richard Yuanzhe  and
      Chen, Angelica  and
      Phang, Jason  and
      Bowman, Samuel R.",
    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.75",
    pages = "1139--1156",
    abstract = "Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries{---}which are nearly always in difficult-to-work-with technical domains{---}or by using approximate heuristics to extract them from everyday text{---}which frequently yields unfaithful summaries. In this work, we turn to a slower but more straightforward approach to developing summarization benchmark data: We hire highly-qualified contractors to read stories and write original summaries from scratch. To amortize reading time, we collect five summaries per document, with the first giving an overview and the subsequent four addressing specific questions. We use this protocol to collect SQuALITY, a dataset of question-focused summaries built on the same public-domain short stories as the multiple-choice dataset QuALITY (Pang et al., 2021). Experiments with state-of-the-art summarization systems show that our dataset is challenging and that existing automatic evaluation metrics are weak indicators of quality.",
}


@article{wang2022squality,
  title={SQuALITY: Building a Long-Document Summarization Dataset the Hard Way},
  author={Wang, Alex and Pang, Richard Yuanzhe and Chen, Angelica and Phang, Jason and Bowman, Samuel R},
  journal={arXiv preprint arXiv:2205.11465},
  year={2022}
}