@inproceedings{jenkins-etal-2023-split,
    title = "To Split or Not to Split: Composing Compounds in Contextual Vector Spaces",
    author = "Jenkins, Chris  and
      Miletic, Filip  and
      Schulte im Walde, Sabine",
    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/add-emnlp-2024-awards/2023.emnlp-main.1002/",
    doi = "10.18653/v1/2023.emnlp-main.1002",
    pages = "16131--16136",
    abstract = "We investigate the effect of sub-word tokenization on representations of German noun compounds: single orthographic words which are composed of two or more constituents but often tokenized into units that are not morphologically motivated or meaningful. Using variants of BERT models and tokenization strategies on domain-specific restricted diachronic data, we introduce a suite of evaluations relying on the masked language modelling task and compositionality prediction. We obtain the most consistent improvements by pre-splitting compounds into constituents."
}