@inproceedings{corro-etal-2025-bregman,
    title = "Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms",
    author = "Corro, Caio  and
      Lacroix, Mathieu  and
      Roux, Joseph Le",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1430/",
    pages = "29557--29574",
    ISBN = "979-8-89176-251-0",
    abstract = "We propose a novel discriminative model for sequence labeling called Bregman conditional random fields (BCRF).Contrary to standard linear-chain conditional random fields,BCRF allows fast parallelizable inference algorithms based on iterative Bregman projections.We show how such models can be learned using Fenchel-Young losses, including extension for learning from partial labels.Experimentally, our approach delivers comparable results to CRF while being faster, and achieves better results in highly constrained settings compared to mean field, another parallelizable alternative."
}