@inproceedings{chiang-yogatama-2023-distributional,
    title = "The Distributional Hypothesis Does Not Fully Explain the Benefits of Masked Language Model Pretraining",
    author = "Chiang, Ting-Rui  and
      Yogatama, Dani",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.emnlp-main.637/",
    doi = "10.18653/v1/2023.emnlp-main.637",
    pages = "10305--10321"
}