@inproceedings{niculae-etal-2018-towards,
    title = "Towards Dynamic Computation Graphs via Sparse Latent Structure",
    author = "Niculae, Vlad  and
      Martins, Andr{\'e} F. T.  and
      Cardie, Claire",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/D18-1108/",
    doi = "10.18653/v1/D18-1108",
    pages = "905--911",
    abstract = "Deep NLP models benefit from underlying structures in the data{---}e.g., parse trees{---}typically extracted using off-the-shelf parsers. Recent attempts to jointly learn the latent structure encounter a tradeoff: either make factorization assumptions that limit expressiveness, or sacrifice end-to-end differentiability. Using the recently proposed SparseMAP inference, which retrieves a sparse distribution over latent structures, we propose a novel approach for end-to-end learning of latent structure predictors jointly with a downstream predictor. To the best of our knowledge, our method is the first to enable unrestricted dynamic computation graph construction from the global latent structure, while maintaining differentiability."
}