@inproceedings{uthus-etal-2023-mlongt5,
    title = "m{L}ong{T}5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences",
    author = "Uthus, David  and
      Ontanon, Santiago  and
      Ainslie, Joshua  and
      Guo, Mandy",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-emnlp.628/",
    doi = "10.18653/v1/2023.findings-emnlp.628",
    pages = "9380--9386",
    abstract = "We present our work on developing a multilingual, efficient text-to-text transformer that is suitable for handling long inputs. This model, called mLongT5, builds upon the architecture of LongT5, while leveraging the multilingual datasets used for pretraining mT5 and the pretraining tasks of UL2. We evaluate this model on a variety of multilingual summarization and question-answering tasks, and the results show stronger performance for mLongT5 when compared to existing multilingual models such as mBART or M-BERT."
}