@inproceedings{lu-etal-2020-multi-xscience,
    title = "Multi-{XS}cience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles",
    author = "Lu, Yao  and
      Dong, Yue  and
      Charlin, Laurent",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2020.emnlp-main.648/",
    doi = "10.18653/v1/2020.emnlp-main.648",
    pages = "8068--8074",
    abstract = "Multi-document summarization is a challenging task for which there exists little large-scale datasets. We propose Multi-XScience, a large-scale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challenging multi-document summarization task: writing the related-work section of a paper based on its abstract and the articles it references. Our work is inspired by extreme summarization, a dataset construction protocol that favours abstractive modeling approaches. Descriptive statistics and empirical results{---}using several state-of-the-art models trained on the Multi-XScience dataset{---}reveal that Multi-XScience is well suited for abstractive models."
}