@inproceedings{xiao-etal-2022-primera,
    title = "{PRIMERA}: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization",
    author = "Xiao, Wen  and
      Beltagy, Iz  and
      Carenini, Giuseppe  and
      Cohan, Arman",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.acl-long.360/",
    doi = "10.18653/v1/2022.acl-long.360",
    pages = "5245--5263",
    abstract = "We introduce PRIMERA, a pre-trained model for multi-document representation with a focus on summarization that reduces the need for dataset-specific architectures and large amounts of fine-tuning labeled data. PRIMERA uses our newly proposed pre-training objective designed to teach the model to connect and aggregate information across documents. It also uses efficient encoder-decoder transformers to simplify the processing of concatenated input documents. With extensive experiments on 6 multi-document summarization datasets from 3 different domains on zero-shot, few-shot and full-supervised settings, PRIMERA outperforms current state-of-the-art dataset-specific and pre-trained models on most of these settings with large margins."
}