@inproceedings{mitchell-etal-2018-extrapolation,
    title = "Extrapolation in {NLP}",
    author = "Mitchell, Jeff  and
      Stenetorp, Pontus  and
      Minervini, Pasquale  and
      Riedel, Sebastian",
    editor = "Bisk, Yonatan  and
      Levy, Omer  and
      Yatskar, Mark",
    booktitle = "Proceedings of the Workshop on Generalization in the Age of Deep Learning",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W18-1005/",
    doi = "10.18653/v1/W18-1005",
    pages = "28--33",
    abstract = "We argue that extrapolation to unseen data will often be easier for models that capture global structures, rather than just maximise their local fit to the training data. We show that this is true for two popular models: the Decomposable Attention Model and word2vec."
}