@inproceedings{nastase-merlo-2024-identifiable,
    title = "Are there identifiable structural parts in the sentence embedding whole?",
    author = "Nastase, Vivi  and
      Merlo, Paola",
    editor = "Belinkov, Yonatan  and
      Kim, Najoung  and
      Jumelet, Jaap  and
      Mohebbi, Hosein  and
      Mueller, Aaron  and
      Chen, Hanjie",
    booktitle = "Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
    month = nov,
    year = "2024",
    address = "Miami, Florida, US",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.blackboxnlp-1.3/",
    doi = "10.18653/v1/2024.blackboxnlp-1.3",
    pages = "23--42",
    abstract = "Sentence embeddings from transformer models encode much linguistic information in a fixed-length vector. We investigate whether structural information {--} specifically, information about chunks and their structural and semantic properties {--} can be detected in these representations. We use a dataset consisting of sentences with known chunk structure, and two linguistic intelligence datasets, whose solution relies on detecting chunks and their grammatical number, and respectively, their semantic roles. Through an approach involving indirect supervision, and through analyses of the performance on the tasks and of the internal representations built during learning, we show that information about chunks and their properties can be obtained from sentence embeddings."
}